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

    Neuronpedia

    INDEX
    Explanations

    imagine, think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inde
    -0.08
    uth
    -0.08
     Bedingungen
    -0.08
    processing
    -0.08
    trusted
    -0.07
     patiently
    -0.07
     refuge
    -0.07
    indir
    -0.07
    initial
    -0.07
    disposing
    -0.07
    POSITIVE LOGITS
     thích
    0.09
    ヨ
    0.09
    コン
    0.08
     french
    0.08
    フ
    0.08
    乙
    0.08
    瑞
    0.08
     calcula
    0.08
    ,.↵↵
    0.08
     предназнач
    0.07
    Act Density 0.001%

    No Known Activations