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

    Neuronpedia

    INDEX
    Explanations

    Title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,o
    -0.07
     nghiêm
    -0.07
    som
    -0.07
     고개를
    -0.06
    ¯
    -0.06
     öl
    -0.06
     cheeks
    -0.06
    reffen
    -0.06
     fest
    -0.06
     Conflict
    -0.06
    POSITIVE LOGITS
    .setTitle
    0.07
     title
    0.07
    icularly
    0.06
    _allow
    0.06
    Turkey
    0.06
    095
    0.06
    BIN
    0.06
    Title
    0.06
    \v
    0.06
    085
    0.06
    Act Density 0.003%

    No Known Activations