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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ə
    -0.07
     Verification
    -0.07
     Peggy
    -0.06
    内の
    -0.06
    (et
    -0.06
     изображ
    -0.06
    topl
    -0.06
    ordova
    -0.06
    атів
    -0.06
     verification
    -0.06
    POSITIVE LOGITS
    ้าม
    0.07
    	group
    0.06
    _ground
    0.06
     intrusive
    0.06
    idis
    0.06
    πί
    0.06
    θυ
    0.06
     lawful
    0.06
    Hours
    0.06
    ]])↵↵
    0.06
    Act Density 0.000%

    No Known Activations