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

    Neuronpedia

    INDEX
    Explanations

    predict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    877
    -0.07
     six
    -0.07
     efforts
    -0.07
     collaborate
    -0.07
     chamber
    -0.06
    6
    -0.06
     forms
    -0.06
    610
    -0.06
     Jas
    -0.06
     Chamber
    -0.06
    POSITIVE LOGITS
     predict
    0.12
     predicted
    0.11
     prediction
    0.09
     Prediction
    0.09
    .predict
    0.09
     Predict
    0.09
    predict
    0.09
     predicts
    0.09
    madı
    0.08
    pred
    0.08
    Act Density 0.029%

    No Known Activations