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

    Neuronpedia

    INDEX
    Explanations

    Code/special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -major
    -0.07
    丽
    -0.07
    Statements
    -0.06
    .UserID
    -0.06
    ोख
    -0.06
    наруж
    -0.06
     Bik
    -0.06
     mourn
    -0.06
     onComplete
    -0.06
     Fifth
    -0.06
    POSITIVE LOGITS
     trolling
    0.07
    나는
    0.06
    joining
    0.06
    (requestCode
    0.06
     참
    0.06
     الل
    0.06
     $_
    0.06
    .c
    0.05
    sell
    0.05
    oret
    0.05
    Act Density 0.223%

    No Known Activations