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

    Neuronpedia

    INDEX
    Explanations

    C/C++ code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ű
    -0.08
     IRepository
    -0.07
    ουλ
    -0.07
    //-
    -0.07
    _reduction
    -0.06
    ,$
    -0.06
    ходит
    -0.06
    '],$
    -0.06
    feedback
    -0.06
    ification
    -0.06
    POSITIVE LOGITS
     SOP
    0.06
    ücken
    0.06
     datingside
    0.06
    _ENCOD
    0.06
    ecurity
    0.06
    Dec
    0.06
    _author
    0.06
    DEC
    0.06
    _->
    0.06
    .squeeze
    0.06
    Act Density 0.012%

    No Known Activations