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

    Neuronpedia

    INDEX
    Explanations

    activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ascii
    -0.07
    :{
↵
    -0.06
     Ukraj
    -0.06
     cadre
    -0.06
    Steps
    -0.06
     믿
    -0.06
    िछल
    -0.06
    茂
    -0.06
     Kerry
    -0.06
    represent
    -0.06
    POSITIVE LOGITS
     продовж
    0.06
    (USER
    0.06
     TRACE
    0.06
     monster
    0.06
     searchText
    0.06
     mez
    0.06
    974
    0.06
    _ends
    0.06
     foto
    0.06
    -meta
    0.06
    Act Density 0.149%

    No Known Activations