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

    Neuronpedia

    INDEX
    Explanations

    channel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cải
    -0.07
    .apps
    -0.07
     manh
    -0.06
    âce
    -0.06
    (back
    -0.06
    大大提高
    -0.06
    iversity
    -0.06
    	ref
    -0.06
    Վ
    -0.06
     У
    -0.06
    POSITIVE LOGITS
    LTR
    0.08
    CRYPT
    0.07
    jur
    0.07
    掭
    0.07
    0.07
    NotAllowed
    0.07
    !</
    0.07
    0.07
    0.07
     IllegalArgumentException
    0.07
    Act Density 0.015%

    No Known Activations