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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ++){↵↵
    -0.08
    lip
    -0.07
    991
    -0.07
    )",↵
    -0.07
    _trial
    -0.07
    цієн
    -0.06
    	str
    -0.06
    qrst
    -0.06
    ประ
    -0.06
    reset
    -0.06
    POSITIVE LOGITS
    -supported
    0.07
     statement
    0.07
    Supported
    0.06
     Indian
    0.06
    (tm
    0.06
     Bened
    0.06
     イ
    0.06
    邦
    0.06
    卡
    0.06
     ford
    0.06
    Act Density 0.276%

    No Known Activations