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

    Neuronpedia

    INDEX
    Explanations

    business documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    תצ
    -0.07
     purpos
    -0.07
    𝕴
    -0.07
    abic
    -0.06
     דקות
    -0.06
    كة
    -0.06
    /navigation
    -0.06
    (numero
    -0.06
     organs
    -0.06
    โส
    -0.06
    POSITIVE LOGITS
    _help
    0.07
    *'
    0.07
     replay
    0.07
     versions
    0.07
    شف
    0.07
     referral
    0.07
    claim
    0.07
    other
    0.06
     Benn
    0.06
    所有情节
    0.06
    Act Density 0.028%

    No Known Activations