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

    Neuronpedia

    INDEX
    Explanations

    explain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .direction
    -0.07
     사용
    -0.07
     에
    -0.07
     throttle
    -0.07
    ⼥
    -0.07
    些什么
    -0.07
    illy
    -0.07
     ích
    -0.07
     gold
    -0.07
    erv
    -0.07
    POSITIVE LOGITS
    noticed
    0.08
    审核
    0.07
    queued
    0.07
    _Find
    0.07
    Lab
    0.07
    作为一种
    0.07
    _VIS
    0.07
    حيا
    0.07
    iciar
    0.06
    REG
    0.06
    Act Density 0.032%

    No Known Activations