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

    Neuronpedia

    INDEX
    Explanations

    accusations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calorie
    -0.07
    igmoid
    -0.06
    音
    -0.06
    -runtime
    -0.06
    cascade
    -0.06
    opian
    -0.06
     cle
    -0.06
     YAML
    -0.06
    比較
    -0.05
     attitudes
    -0.05
    POSITIVE LOGITS
     accusations
    0.10
     accusation
    0.10
     accusing
    0.09
     charged
    0.09
     allegations
    0.08
     Charges
    0.08
     charges
    0.07
     loadChildren
    0.07
     accus
    0.07
     allegation
    0.07
    Act Density 0.020%

    No Known Activations