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

    Neuronpedia

    INDEX
    Explanations

    finish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     targeted
    -0.08
    arg
    -0.07
     recherche
    -0.07
    син
    -0.07
    $search
    -0.07
    Searching
    -0.07
    GetType
    -0.07
    _hash
    -0.06
    .isValid
    -0.06
    shows
    -0.06
    POSITIVE LOGITS
     oxid
    0.08
    三个月
    0.07
    ⥄
    0.07
    蚌
    0.07
    遂
    0.07
     additions
    0.07
    佩服
    0.07
    不免
    0.07
     finanzi
    0.07
     EXIT
    0.07
    Act Density 0.012%

    No Known Activations