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

    Neuronpedia

    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nego
    -0.07
    allocate
    -0.07
     정부
    -0.07
    capt
    -0.07
     ท
    -0.06
     Boris
    -0.06
    ':↵↵
    -0.06
     Woo
    -0.06
     juego
    -0.06
    whose
    -0.06
    POSITIVE LOGITS
    ,width
    0.06
    -limit
    0.06
     misery
    0.06
     ''}↵
    0.06
    ่างก
    0.06
    žení
    0.06
    taj
    0.06
    subseteq
    0.06
    窗
    0.06
    udd
    0.06
    Act Density 0.056%

    No Known Activations