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

    Neuronpedia

    INDEX
    Explanations

    forward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mine
    -0.07
     notamment
    -0.07
    ันเป
    -0.07
     MOR
    -0.06
    UTH
    -0.06
    -bearing
    -0.06
     �
    -0.06
    arently
    -0.06
     веч
    -0.06
    Problem
    -0.06
    POSITIVE LOGITS
     війни
    0.07
     scaler
    0.06
    декс
    0.06
     efficacy
    0.06
    client
    0.06
     superclass
    0.06
    /disable
    0.06
    active
    0.06
    �
    0.06
    wick
    0.06
    Act Density 0.002%

    No Known Activations