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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __[
    -0.07
     getNode
    -0.06
     UNU
    -0.06
     prized
    -0.06
    WithURL
    -0.06
     fractions
    -0.06
     inspires
    -0.06
    publication
    -0.06
     haben
    -0.06
     BELOW
    -0.06
    POSITIVE LOGITS
     нес
    0.07
    _floor
    0.06
     reels
    0.06
     �
    0.06
    Android
    0.06
    (column
    0.06
    ael
    0.06
     thrott
    0.06
    eza
    0.06
    coal
    0.06
    Act Density 0.013%

    No Known Activations