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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sku
    -0.07
    liness
    -0.07
     بايد
    -0.07
    Ž
    -0.07
    Et
    -0.07
     eigentlich
    -0.07
     fotbal
    -0.06
     Beh
    -0.06
    대
    -0.06
    (Dialog
    -0.06
    POSITIVE LOGITS
     stakeholders
    0.07
     Anthem
    0.06
     Functions
    0.06
     CB
    0.06
     Commentary
    0.06
     reduce
    0.06
     Wrap
    0.06
    ahoo
    0.06
     großen
    0.06
     '',
↵
    0.06
    Act Density 0.159%

    No Known Activations