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

    Neuronpedia

    INDEX
    Explanations

    causal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     повідом
    -0.07
     boyunca
    -0.06
    يران
    -0.06
     loans
    -0.06
     algebra
    -0.06
    /build
    -0.06
    ían
    -0.06
     Trees
    -0.06
     quanto
    -0.06
     build
    -0.06
    POSITIVE LOGITS
    asic
    0.07
    val
    0.07
     修改
    0.07
    @email
    0.06
    astreet
    0.06
    versed
    0.06
    uggling
    0.06
    ательно
    0.06
    asons
    0.06
    VAL
    0.06
    Act Density 0.003%

    No Known Activations