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

    Neuronpedia

    INDEX
    Explanations

    red

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     banned
    -0.07
     웨
    -0.06
    ستر
    -0.06
     entering
    -0.06
     Internet
    -0.06
    terminate
    -0.06
    *A
    -0.06
    isos
    -0.06
    原本
    -0.06
     sebou
    -0.06
    POSITIVE LOGITS
    _VIRTUAL
    0.06
    514
    0.06
    691
    0.06
    869
    0.06
    argout
    0.06
    すれば
    0.06
    .ejb
    0.06
    @(
    0.06
    lediği
    0.06
     jar
    0.06
    Act Density 0.005%

    No Known Activations