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

    Neuronpedia

    INDEX
    Explanations

    reject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alfred
    -0.07
     hablar
    -0.06
     cantidad
    -0.06
     Aqua
    -0.06
    ampled
    -0.06
     UIGraphics
    -0.06
    Svc
    -0.06
     Teach
    -0.06
    uka
    -0.06
    .textBox
    -0.06
    POSITIVE LOGITS
     Reject
    0.08
     rejection
    0.08
    _ctr
    0.08
     each
    0.07
     rejected
    0.07
    339
    0.07
     reject
    0.07
     injecting
    0.06
    _rhs
    0.06
     Romney
    0.06
    Act Density 0.007%

    No Known Activations