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

    Neuronpedia

    INDEX
    Explanations

    Witness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ivy
    -0.07
     noir
    -0.07
    �藏
    -0.07
    _Code
    -0.06
    142
    -0.06
    _FREE
    -0.06
     abortion
    -0.06
    .Nodes
    -0.06
     $
    -0.06
     Configuration
    -0.06
    POSITIVE LOGITS
     witnesses
    0.11
     witness
    0.10
     Witness
    0.08
    Witness
    0.08
     witnessed
    0.08
     witnessing
    0.08
     eyewitness
    0.08
     Witnesses
    0.07
     Vince
    0.07
    cry
    0.07
    Act Density 0.004%

    No Known Activations