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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $q
    -0.07
     noble
    -0.07
    _eta
    -0.06
     PDT
    -0.06
    '):
↵
    -0.06
    $message
    -0.06
    _cap
    -0.06
    ,o
    -0.06
     Sacramento
    -0.06
    _trap
    -0.06
    POSITIVE LOGITS
     persisted
    0.07
     PROJECT
    0.07
    inject
    0.06
     succinct
    0.06
    unter
    0.06
    色的
    0.06
    -team
    0.06
    anio
    0.06
     ans
    0.06
     stir
    0.06
    Act Density 0.062%

    No Known Activations