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

    Neuronpedia

    INDEX
    Explanations

    spread

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    경영
    -0.06
    cosa
    -0.06
     различных
    -0.06
     гос
    -0.06
     vnode
    -0.06
    влечен
    -0.06
     Games
    -0.06
    рин
    -0.06
     abs
    -0.06
    velle
    -0.06
    POSITIVE LOGITS
    Fra
    0.07
    持仓
    0.07
    ALLEL
    0.07
     Injector
    0.07
    扫码
    0.07
     getField
    0.07
     stacked
    0.07
    _cluster
    0.07
    clicked
    0.07
    /custom
    0.07
    Act Density 0.003%

    No Known Activations