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

    Neuronpedia

    INDEX
    Explanations

    Contractions and possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Greeks
    -0.07
    adc
    -0.06
    Senate
    -0.06
     Parallel
    -0.06
    第一
    -0.06
    IDENT
    -0.06
    ications
    -0.06
    _TW
    -0.06
     signage
    -0.06
     RESET
    -0.06
    POSITIVE LOGITS
     stør
    0.06
    otoxic
    0.06
    "data
    0.06
    okol
    0.06
    (tid
    0.06
    intl
    0.06
     короб
    0.06
    conn
    0.06
     localization
    0.06
    ола
    0.06
    Act Density 0.330%

    No Known Activations