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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typeName
    -0.07
    _("
    -0.07
    兩
    -0.06
    surf
    -0.06
    ược
    -0.06
    dto
    -0.06
     Accessed
    -0.06
    Disconnected
    -0.06
    руш
    -0.06
    诺
    -0.06
    POSITIVE LOGITS
    ulia
    0.07
    _EDIT
    0.07
    AMIL
    0.06
     Incorpor
    0.06
    August
    0.06
    vání
    0.06
     compens
    0.06
     escrit
    0.06
    iltro
    0.06
     Person
    0.06
    Act Density 0.157%

    No Known Activations