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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    euillez
    -0.07
    .integration
    -0.07
     Cors
    -0.07
     Hàn
    -0.07
    .DEFAULT
    -0.06
     Chess
    -0.06
    Dto
    -0.06
     Lyons
    -0.06
     Dod
    -0.06
     SUP
    -0.06
    POSITIVE LOGITS
     Contracts
    0.06
     derivation
    0.06
    fit
    0.06
    _child
    0.06
     neither
    0.06
     Proposition
    0.06
     Gre
    0.06
     trg
    0.06
    力的
    0.06
    Logo
    0.06
    Act Density 0.096%

    No Known Activations