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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rh
    -0.07
    óc
    -0.06
    被盗
    -0.06
    ]])
    -0.06
    lsruhe
    -0.06
    醒
    -0.06
     inv
    -0.06
    三年
    -0.06
     Phon
    -0.06
     Login
    -0.06
    POSITIVE LOGITS
    ∩
    0.07
    >Hello
    0.07
    يمة
    0.07
     THANK
    0.07
    ⟪
    0.07
    WR
    0.07
    厥
    0.06
    POWER
    0.06
    领导下
    0.06
     terminator
    0.06
    Act Density 0.001%

    No Known Activations