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

    Neuronpedia

    INDEX
    Explanations

    Code and number strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cef
    -0.07
     couple
    -0.06
     מדוע
    -0.06
    unbind
    -0.06
     chiar
    -0.06
    �
    -0.06
    ('../../../
    -0.06
    -placeholder
    -0.06
     Fetish
    -0.06
    viously
    -0.06
    POSITIVE LOGITS
     сл
    0.07
    NR
    0.07
     sucks
    0.07
     FD
    0.07
    _Window
    0.07
    艨
    0.07
    &gt
    0.07
    .reflect
    0.07
    entropy
    0.07
     בעל
    0.06
    Act Density 0.017%

    No Known Activations