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

    Neuronpedia

    INDEX
    Explanations

    wid widow WD ym

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dev
    0.37
    <unused548>
    0.37
     oddly
    0.37
    ParameterActive
    0.36
    เวล
    0.36
    <unused56>
    0.36
     considerazione
    0.36
     Freitas
    0.36
     DEPENDENCIA
    0.35
    riter
    0.35
    POSITIVE LOGITS
     directed
    0.43
     Wid
    0.43
    wid
    0.40
    post
    0.40
     greeting
    0.40
    paren
    0.39
     باز
    0.39
     wid
    0.39
    ificate
    0.38
    Wid
    0.38
    Act Density 0.005%

    No Known Activations