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

    Neuronpedia

    INDEX
    Explanations

    Non-English text/sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سفر
    -0.07
     discomfort
    -0.07
    promotion
    -0.07
    ertino
    -0.07
    Charles
    -0.06
     началь
    -0.06
    .jd
    -0.06
    civil
    -0.06
     Bruce
    -0.06
     sublime
    -0.06
    POSITIVE LOGITS
    邮箱
    0.07
    OUT
    0.06
    	audio
    0.06
    DidChange
    0.06
    ्ययन
    0.06
    DIV
    0.06
    �
    0.06
    )row
    0.06
     υπάρχ
    0.06
    )，
    0.06
    Act Density 0.136%

    No Known Activations