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

    Neuronpedia

    INDEX
    Explanations

    To

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الأك
    -0.07
    μένα
    -0.07
    arem
    -0.06
    <D
    -0.06
    Bir
    -0.06
    -breaking
    -0.06
    WithEmail
    -0.06
     акт
    -0.06
     principalmente
    -0.06
    ;r
    -0.06
    POSITIVE LOGITS
    .obs
    0.07
    少年
    0.07
    	method
    0.06
    ecome
    0.06
    Offsets
    0.06
    Module
    0.06
     Buch
    0.06
    都市
    0.06
     coordinates
    0.06
     Fe
    0.06
    Act Density 0.000%

    No Known Activations