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

    Neuronpedia

    INDEX
    Explanations

    code and data structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IRONMENT
    0.40
     stoichi
    0.39
    ILABLE
    0.37
     thisobject
    0.36
    ⏤
    0.36
     FODC
    0.36
    StudentNo
    0.35
     Apica
    0.35
     spiderY
    0.35
    ();//
    0.35
    POSITIVE LOGITS
    ↵
    0.42
     F
    0.33
    be
    0.31
    ize
    0.31
    de
    0.30
    ↵↵↵
    0.29
    ise
    0.29
    d
    0.29
     D
    0.28
    0.28
    Act Density 0.105%

    No Known Activations