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

    Neuronpedia

    INDEX
    Explanations

    SparkSession creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ENDMENT
    0.44
     સ્ટ
    0.40
    毽
    0.40
    湿
    0.37
    Contato
    0.37
    Service
    0.36
    Approach
    0.36
    Pojo
    0.36
     dérou
    0.36
    दित
    0.36
    POSITIVE LOGITS
    脂
    0.43
     bassist
    0.38
     labels
    0.38
    raz
    0.38
    labels
    0.38
     Kuhn
    0.37
    ラベル
    0.37
    rownames
    0.37
     Labels
    0.36
    Stderr
    0.36
    Act Density 0.001%

    No Known Activations