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

    Neuronpedia

    INDEX
    Explanations

    predict, make

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     forfait
    -0.08
     interrom
    -0.08
    ny
    -0.08
    Titel
    -0.07
     celebra
    -0.07
     crate
    -0.07
    প্ন
    -0.07
    Brains
    -0.07
    Frm
    -0.07
    POSITIVE LOGITS
     predictions
    0.17
     Predictions
    0.15
     observable
    0.15
     predicted
    0.14
     predicts
    0.14
     predict
    0.13
    预测
    0.13
     voorsp
    0.12
     predicting
    0.12
    observable
    0.12
    Act Density 0.008%

    No Known Activations