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

    Neuronpedia

    INDEX
    Explanations

    code markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    👃
    -0.07
     Tig
    -0.07
     skal
    -0.07
    🛁
    -0.07
    onChange
    -0.07
     betr
    -0.07
     again
    -0.07
     rencont
    -0.07
     true
    -0.07
     appears
    -0.07
    POSITIVE LOGITS
    iative
    0.07
    students
    0.07
    fld
    0.07
    feeding
    0.07
    lies
    0.07
     Launcher
    0.07
    .ToArray
    0.07
     ordering
    0.07
    垢
    0.06
    sampling
    0.06
    Act Density 0.012%

    No Known Activations