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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     birthday
    -0.08
     perfect
    -0.08
     atm
    -0.08
     tones
    -0.07
    )`
    -0.07
    ’t
    -0.07
    Save
    -0.07
     measured
    -0.07
     Army
    -0.07
    -to
    -0.07
    POSITIVE LOGITS
    ":["
    0.07
     рад
    0.06
    ...(
    0.06
    ......
    0.06
     Єв
    0.06
    	lcd
    0.06
     역시
    0.06
    .cd
    0.06
    620
    0.06
    ัฒ
    0.06
    Act Density 0.082%

    No Known Activations