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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;$
    0.57
     bebê
    0.52
    megaphone
    0.51
    .(\
    0.51
    📥
    0.51
    ्राफी
    0.50
    desa
    0.50
    $[\
    0.50
    besie
    0.50
    +$
    0.50
    POSITIVE LOGITS
    T
    0.57
     Sub
    0.52
     Of
    0.51
    S
    0.51
     Ser
    0.50
     Al
    0.49
     Crow
    0.48
     Kinh
    0.47
     Qu
    0.47
    tas
    0.46
    Act Density 0.000%

    No Known Activations