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

    Neuronpedia

    INDEX
    Explanations

    negative impacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interests
    -0.99
     Interests
    -0.82
     harm
    -0.79
     harms
    -0.75
    interests
    -0.73
     grounds
    -0.69
     contacts
    -0.66
    Interests
    -0.66
     ProtoMessage
    -0.61
     interesses
    -0.58
    POSITIVE LOGITS
    ⓧ
    0.62
    requireNonNull
    0.60
     doInBackground
    0.59
     propOrder
    0.57
     sanitaires
    0.56
    choenen
    0.56
     numériques
    0.56
     zondag
    0.56
     resourceCulture
    0.56
     célèbres
    0.56
    Act Density 0.062%

    No Known Activations