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

    Neuronpedia

    INDEX
    Explanations

    versus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Child
    -0.07
     opat
    -0.07
     thôn
    -0.06
     aloud
    -0.06
    14
    -0.06
    13
    -0.06
    ाहर
    -0.06
     كامل
    -0.06
     삼
    -0.06
    15
    -0.06
    POSITIVE LOGITS
     versus
    0.15
     vs
    0.15
     VS
    0.10
    VS
    0.09
    vs
    0.09
     Vs
    0.09
    us
    0.07
    _vs
    0.07
    .vs
    0.07
    os
    0.07
    Act Density 0.012%

    No Known Activations