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

    Neuronpedia

    INDEX
    Explanations

    thought

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cu
    -0.07
    55
    -0.07
     sudo
    -0.07
     ace
    -0.07
     applaud
    -0.06
     lids
    -0.06
    sudo
    -0.06
    .Bl
    -0.06
    _ax
    -0.06
     tea
    -0.06
    POSITIVE LOGITS
     حول
    0.07
     uninterrupted
    0.06
     пут
    0.06
     ترب
    0.06
    TERN
    0.06
    ticker
    0.06
     formulations
    0.06
    _behavior
    0.06
     feared
    0.06
    .Inv
    0.06
    Act Density 0.029%

    No Known Activations