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

    Neuronpedia

    INDEX
    Explanations

    thinking and observation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aged
    -0.07
    仓
    -0.06
    イド
    -0.06
     以
    -0.06
    Thing
    -0.06
    收
    -0.06
    ैप
    -0.06
     enviado
    -0.06
    .setter
    -0.06
    cura
    -0.06
    POSITIVE LOGITS
    _occ
    0.06
     Forbidden
    0.06
    onomies
    0.06
    ậc
    0.06
     đem
    0.06
     सल
    0.06
    -member
    0.06
    bond
    0.06
     квар
    0.06
     biz
    0.06
    Act Density 0.129%

    No Known Activations