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

    Neuronpedia

    INDEX
    Explanations

    h

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    溪
    -0.08
    짘
    -0.07
    uell
    -0.07
    lead
    -0.07
     î
    -0.07
     Keeper
    -0.07
     utility
    -0.07
    申请人
    -0.07
     addItem
    -0.07
     full
    -0.07
    POSITIVE LOGITS
     architectures
    0.07
     behaviours
    0.07
    intersect
    0.07
    ⋈
    0.06
    是国内
    0.06
     Socket
    0.06
     forging
    0.06
     genotype
    0.06
    (Handle
    0.06
    ******↵↵
    0.06
    Act Density 0.004%

    No Known Activations