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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utdown
    -0.07
    .repo
    -0.06
    oreach
    -0.06
    ftype
    -0.06
    fung
    -0.06
    .ToInt
    -0.06
    Validators
    -0.06
    ัค
    -0.06
    _BREAK
    -0.06
    ิจารณ
    -0.06
    POSITIVE LOGITS
    ohn
    0.07
     deine
    0.07
     ACT
    0.06
     ')
↵
    0.06
     loophole
    0.06
     사이트
    0.06
     Ahmet
    0.06
     bilinen
    0.06
     aunque
    0.06
     usernames
    0.06
    Act Density 0.031%

    No Known Activations