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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Visibility
    -0.07
    571
    -0.07
     jag
    -0.07
     Expo
    -0.07
    214
    -0.07
    _nh
    -0.07
     rejected
    -0.07
    安
    -0.07
     pin
    -0.07
    _TRANSL
    -0.07
    POSITIVE LOGITS
    _'
    0.06
    amins
    0.06
    vrir
    0.06
     emin
    0.06
    glm
    0.06
     Includes
    0.06
    feel
    0.06
    GetSize
    0.05
    /views
    0.05
     looked
    0.05
    Act Density 0.281%

    No Known Activations