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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     render
    -0.07
     mẽ
    -0.07
     wool
    -0.07
    ;y
    -0.06
    ecial
    -0.06
     Entr
    -0.06
     vorhand
    -0.06
    -counter
    -0.06
    yi
    -0.06
    POSITIVE LOGITS
     hacks
    0.06
     Rivera
    0.06
    .{
    0.06
     Arrest
    0.06
     Gand
    0.06
    ination
    0.06
    Captain
    0.06
    flags
    0.06
     hack
    0.06
     formulas
    0.06
    Act Density 0.000%

    No Known Activations