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

    Neuronpedia

    INDEX
    Explanations

    numerical scales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imagePath
    -0.07
     �
    -0.07
    _media
    -0.06
     Sicher
    -0.06
    apeut
    -0.06
     kön
    -0.06
     τά
    -0.06
     thresholds
    -0.06
    τών
    -0.06
    El
    -0.06
    POSITIVE LOGITS
    ційно
    0.06
    OR
    0.06
    modo
    0.06
    -ex
    0.06
     investor
    0.06
    /export
    0.05
     distractions
    0.05
     criticisms
    0.05
     vr
    0.05
    overflow
    0.05
    Act Density 0.004%

    No Known Activations