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

    Neuronpedia

    INDEX
    Explanations

    terms related to errors and limitations in processes or systems

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

    problems and difficulties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.54
    PYX
    -0.51
    SequentialGroup
    -0.50
    AddTagHelper
    -0.50
     CreateTagHelper
    -0.49
     שוליים
    -0.49
     насељу
    -0.48
    IInterface
    -0.47
     Numerade
    -0.47
    lotl
    -0.46
    POSITIVE LOGITS
     conquist
    0.36
     utafitiHapana
    0.35
     Velasco
    0.32
    umask
    0.32
    iasaan
    0.32
     kecepatan
    0.32
    さっき
    0.31
    ョ
    0.31
    Faster
    0.30
    guisement
    0.30
    Act Density 0.294%

    No Known Activations