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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Concat
    -0.06
    +'"
    -0.06
    ``
    -0.06
     Strike
    -0.06
    Destroy
    -0.06
     EventType
    -0.06
    ]=='
    -0.06
    ArrayList
    -0.06
    _Callback
    -0.06
     Finch
    -0.06
    POSITIVE LOGITS
     fieldName
    0.07
    0
    0.07
    Κ
    0.07
    ंपन
    0.07
    5
    0.06
    워크
    0.06
    ề
    0.06
    容
    0.06
     E
    0.06
    ик
    0.06
    Act Density 1.232%

    No Known Activations