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

    Neuronpedia

    INDEX
    Explanations

    Names/Titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    629
    -0.07
    偷
    -0.07
     فو
    -0.07
    achs
    -0.06
    .fac
    -0.06
     Spec
    -0.06
     recru
    -0.06
    “At
    -0.06
    人が
    -0.06
     Hydraulic
    -0.06
    POSITIVE LOGITS
     ensure
    0.07
    _EXPORT
    0.07
    .Promise
    0.07
     realised
    0.07
    Capture
    0.06
     %@",
    0.06
    OK
    0.06
    OULD
    0.06
    ?!
    0.06
    ALLENG
    0.06
    Act Density 0.025%

    No Known Activations