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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jejich
    -0.07
    一
    -0.07
     moderation
    -0.07
    .NAME
    -0.06
    折
    -0.06
     así
    -0.06
    博士
    -0.06
    monds
    -0.06
     vých
    -0.06
    _fragment
    -0.06
    POSITIVE LOGITS
    (sem
    0.06
    �
    0.06
    _totals
    0.06
    徒
    0.06
    prep
    0.06
     superhero
    0.06
    _CALLBACK
    0.06
    accel
    0.06
    capability
    0.06
     DCHECK
    0.06
    Act Density 0.020%

    No Known Activations