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

    Neuronpedia

    INDEX
    Explanations

    empathy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loot
    -0.07
     Priv
    -0.07
     decorations
    -0.07
    ition
    -0.07
     지난
    -0.07
    decoded
    -0.07
     dv
    -0.06
    coes
    -0.06
     Berg
    -0.06
     Receipt
    -0.06
    POSITIVE LOGITS
     empathy
    0.08
     menos
    0.07
    StringRef
    0.07
    .That
    0.07
     empath
    0.06
    Hip
    0.06
    EM
    0.06
     Нет
    0.06
    思
    0.06
     hypothesis
    0.06
    Act Density 0.007%

    No Known Activations