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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trabaj
    -0.07
    kat
    -0.07
    :host
    -0.07
    loops
    -0.06
    IMP
    -0.06
     RTP
    -0.06
    ją
    -0.06
     hud
    -0.06
     referee
    -0.06
    hos
    -0.06
    POSITIVE LOGITS
     pipelines
    0.07
     iam
    0.06
    glob
    0.06
     datingside
    0.06
    asInstanceOf
    0.06
     학교
    0.06
     FileUtils
    0.06
    /fwlink
    0.06
     万元
    0.06
     wiring
    0.06
    Act Density 0.003%

    No Known Activations