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

    Neuronpedia

    INDEX
    Explanations

    Encryption characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diana
    -0.08
    agner
    -0.07
    ראי
    -0.07
     Driving
    -0.07
    事后
    -0.06
     conveyed
    -0.06
    죄
    -0.06
     Right
    -0.06
    _DP
    -0.06
    _interaction
    -0.06
    POSITIVE LOGITS
    ╱
    0.07
     emulate
    0.07
    larg
    0.07
     einem
    0.07
    nier
    0.07
    鹬
    0.07
    とする
    0.07
    Kent
    0.07
    是什么呢
    0.06
    问我
    0.06
    Act Density 0.003%

    No Known Activations