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

    Neuronpedia

    INDEX
    Explanations

    language and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Detalles
    0.59
    tcpHeader
    0.57
     zien
    0.55
     Ljublj
    0.54
    ⩾
    0.54
    ≳
    0.52
     Dependence
    0.49
    ᠴ
    0.49
     ideia
    0.49
     Bücher
    0.49
    POSITIVE LOGITS
    1
    0.56
    2
    0.55
    3
    0.55
     to
    0.54
     силу
    0.51
    8
    0.49
     act
    0.48
     essence
    0.48
     abe
    0.48
     actuation
    0.47
    Act Density 0.000%

    No Known Activations