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

    Neuronpedia

    INDEX
    Explanations

    Spoilers ahead/below/follow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    longrightarrow
    -0.07
    simp
    -0.07
     shameful
    -0.07
     Colum
    -0.07
     Rush
    -0.07
    куля
    -0.07
     Critical
    -0.07
    _remote
    -0.06
     sql
    -0.06
    /pm
    -0.06
    POSITIVE LOGITS
    }↵↵↵↵
    0.06
     Fresno
    0.06
    oldown
    0.06
    _PRIVATE
    0.06
    -Sep
    0.05
    드립니다
    0.05
    했습니다
    0.05
     อย
    0.05
     handled
    0.05
     atd
    0.05
    Act Density 0.013%

    No Known Activations