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

    Neuronpedia

    INDEX
    Explanations

    Code and game related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tasted
    -0.07
     rubbed
    -0.06
     POD
    -0.06
     обращ
    -0.06
     Chương
    -0.06
    σια
    -0.06
    �
    -0.06
     ظ
    -0.06
     randomness
    -0.06
    保護
    -0.06
    POSITIVE LOGITS
     peníze
    0.07
     zástup
    0.07
     ек
    0.07
     discipline
    0.06
    egal
    0.06
     خود
    0.06
    keys
    0.06
     num
    0.06
    (phone
    0.06
    	max
    0.06
    Act Density 0.013%

    No Known Activations