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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    go
    -0.08
     combine
    -0.07
    [*
    -0.07
    RET
    -0.07
     cabo
    -0.06
     Proper
    -0.06
    (*
    -0.06
    сього
    -0.06
    ания
    -0.06
     этих
    -0.06
    POSITIVE LOGITS
     reserves
    0.06
     remarked
    0.06
    aussian
    0.06
     hostname
    0.06
    .raises
    0.06
     ngOnInit
    0.06
    \Http
    0.06
     AndAlso
    0.06
     Steve
    0.06
    rists
    0.06
    Act Density 0.015%

    No Known Activations