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

    Neuronpedia

    INDEX
    Explanations

    expressions of value and appreciation

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

    Appreciation or value

    np_acts-logits-general · gemini-2.0-flash

    assigning worth or importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Domínguez
    -0.51
     utafitiHapana
    -0.46
     rigged
    -0.44
    ientôt
    -0.44
    ⎩
    -0.41
    Automatically
    -0.41
    Swim
    -0.41
     Efq
    -0.40
     Dö
    -0.40
    WithFormat
    -0.40
    POSITIVE LOGITS
     appreciates
    0.69
     précieux
    0.69
     appreciated
    0.67
     appreciating
    0.67
     valued
    0.67
     appreciate
    0.67
     waarde
    0.66
     Valuable
    0.66
    valuable
    0.63
     valioso
    0.63
    Act Density 0.093%

    No Known Activations