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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ąd
    -0.07
    aptors
    -0.07
     Porter
    -0.06
    _mtx
    -0.06
     Doc
    -0.06
    .Components
    -0.06
     kinky
    -0.06
     Record
    -0.06
    .bad
    -0.06
    ورش
    -0.06
    POSITIVE LOGITS
     Kills
    0.07
    (Blueprint
    0.07
    (Exception
    0.06
     crib
    0.06
    /stdc
    0.06
     خوش
    0.06
    _ssh
    0.06
    Ö
    0.06
     عملية
    0.06
     Osc
    0.06
    Act Density 0.039%

    No Known Activations