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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     satisfy
    -0.07
    Ve
    -0.07
     accrued
    -0.06
    (dateTime
    -0.06
     awake
    -0.06
    .home
    -0.06
     benefits
    -0.06
     generous
    -0.06
    _ALIGNMENT
    -0.06
    GI
    -0.06
    POSITIVE LOGITS
     Mühendis
    0.07
     Alec
    0.07
     }}"
    0.07
     poets
    0.07
    //----------------------------------------------------------------------------------------------------------------
    0.06
    InstantiationException
    0.06
    .Monad
    0.06
    θεση
    0.06
     Celtics
    0.06
    _INV
    0.06
    Act Density 0.001%

    No Known Activations