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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _endpoint
    -0.08
    р
    -0.07
    名字
    -0.06
    44
    -0.06
    IDs
    -0.06
     з
    -0.06
    ments
    -0.06
    医
    -0.06
    evil
    -0.06
    90
    -0.06
    POSITIVE LOGITS
     LETTER
    0.07
     форм
    0.07
     Programmer
    0.06
     çev
    0.06
     Donne
    0.06
     SpringApplication
    0.06
    contri
    0.06
    _SIGN
    0.06
     imper
    0.06
    .parseColor
    0.06
    Act Density 0.022%

    No Known Activations