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

    Neuronpedia

    INDEX
    Explanations

    to the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Origin
    -0.07
    [field
    -0.06
    167
    -0.06
    183
    -0.06
    REMOVE
    -0.06
    ivic
    -0.06
     Suche
    -0.06
     Lecture
    -0.06
    .singleton
    -0.06
     трех
    -0.06
    POSITIVE LOGITS
     intercepted
    0.08
    诉
    0.07
    ひと
    0.07
    isinin
    0.07
     imposed
    0.06
    abbrev
    0.06
    сион
    0.06
    ρας
    0.06
     ApiException
    0.06
    iedo
    0.06
    Act Density 0.003%

    No Known Activations