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

    Neuronpedia

    INDEX
    Explanations

    Daly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    47
    -0.07
     информа
    -0.07
     Introduction
    -0.06
    /features
    -0.06
    esters
    -0.06
     freder
    -0.06
     hectic
    -0.06
    ("`
    -0.06
     Leo
    -0.06
     setter
    -0.06
    POSITIVE LOGITS
    ál
    0.08
    ального
    0.08
    ale
    0.08
    AL
    0.08
     Walton
    0.08
    alle
    0.08
    alie
    0.08
    ald
    0.07
    _base
    0.07
    _BAL
    0.07
    Act Density 0.092%

    No Known Activations