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

    Neuronpedia

    INDEX
    Explanations

    comma and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    924
    -0.08
    _bt
    -0.07
    .quant
    -0.07
    (bytes
    -0.07
     η
    -0.06
     disbelief
    -0.06
     Paris
    -0.06
    72
    -0.06
    Fault
    -0.06
    cancellationToken
    -0.06
    POSITIVE LOGITS
     Cue
    0.07
    included
    0.07
    edir
    0.06
    ldr
    0.06
    daf
    0.06
    érer
    0.06
     뭐
    0.06
    Tier
    0.06
    hk
    0.06
    fos
    0.06
    Act Density 0.037%

    No Known Activations