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

    Neuronpedia

    INDEX
    Explanations

    Altruism and helping others

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clen
    -0.07
    Titles
    -0.07
    昌
    -0.07
     massively
    -0.06
     하루
    -0.06
    AppComponent
    -0.06
     Tale
    -0.06
    UU
    -0.06
     cơm
    -0.06
     millennials
    -0.06
    POSITIVE LOGITS
    (Yii
    0.07
    .emptyList
    0.07
    .mouse
    0.07
    -download
    0.06
    ypress
    0.06
    ithub
    0.06
     Spider
    0.06
     Rica
    0.06
    \xd
    0.06
     polov
    0.06
    Act Density 0.203%

    No Known Activations