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

    Neuronpedia

    INDEX
    Explanations

    sensitive or challenging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >[]
    -0.08
    (Output
    -0.08
     Angie
    -0.07
     추진
    -0.07
     indu
    -0.07
    になりました
    -0.07
     mưa
    -0.07
     tap
    -0.07
     Compar
    -0.07
    驽
    -0.07
    POSITIVE LOGITS
    彩色
    0.07
    kit
    0.07
    Pix
    0.07
    קת
    0.06
    pad
    0.06
    爱
    0.06
    ế
    0.06
    Č
    0.06
    𝐒
    0.06
    ronic
    0.06
    Act Density 0.131%

    No Known Activations