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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }</
    -0.07
     Healthy
    -0.06
    ?>&
    -0.06
    ]-
    -0.06
    Prediction
    -0.06
    -)
    -0.06
     AG
    -0.06
     "/
    -0.06
    ření
    -0.06
    	Common
    -0.06
    POSITIVE LOGITS
    jt
    0.07
    visející
    0.07
    gar
    0.06
     �
    0.06
     Scala
    0.06
     kaps
    0.06
    เปล
    0.06
    OI
    0.06
    preh
    0.06
    34
    0.06
    Act Density 0.005%

    No Known Activations