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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evacuate
    -0.08
     EC
    -0.08
    UCH
    -0.07
     infected
    -0.07
    assigned
    -0.07
     traversal
    -0.07
     mia
    -0.07
    	send
    -0.07
     EF
    -0.07
    戰
    -0.06
    POSITIVE LOGITS
    ありました
    0.07
     öğrenciler
    0.07
    Peripheral
    0.06
     apartheid
    0.06
    뻤
    0.06
    换成
    0.06
    前置
    0.06
    去哪里
    0.06
     PlayStation
    0.06
    シェ
    0.06
    Act Density 0.009%

    No Known Activations