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

    Neuronpedia

    INDEX
    Explanations

    code validation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⍨
    -0.08
    送上
    -0.07
    ]:
↵
    -0.07
    会议上
    -0.06
    大佬
    -0.06
    错过了
    -0.06
     Ying
    -0.06
    Allow
    -0.06
     BRA
    -0.06
    พวกเขา
    -0.06
    POSITIVE LOGITS
    vl
    0.07
    Survey
    0.07
    ENDOR
    0.07
    /schema
    0.07
    _ratings
    0.07
    PDO
    0.07
    ueblo
    0.07
    샙
    0.07
    emi
    0.06
    ifa
    0.06
    Act Density 0.003%

    No Known Activations