Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to loss and its different contexts or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "loss" and its related forms

    np_acts-logits-general · gemini-2.0-flash

    loss of X, loss leader, lossless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.83
    OGND
    -0.82
     nahilalakip
    -0.78
     />\
    -0.71
     resourceCulture
    -0.69
     "..\..\
    -0.67
    ilogue
    -0.65
     referenties
    -0.64
    ItemBackground
    -0.63
     surla
    -0.63
    POSITIVE LOGITS
     Loss
    0.90
    Loss
    0.90
     LOSS
    0.89
    loss
    0.87
     loss
    0.85
    LOSS
    0.85
     losses
    0.83
    Losses
    0.83
     Losses
    0.83
     incurred
    0.78
    Act Density 0.075%

    No Known Activations