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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and subscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +
    0.71
     symplectic
    0.66
    будь
    0.65
     grammat
    0.65
     fom
    0.65
    慳
    0.63
     Kilometer
    0.63
     GDPR
    0.61
     Brain
    0.61
     sebum
    0.61
    POSITIVE LOGITS
    <sub>
    1.29
    _{
    1.14
    _{\
    1.03
     _{
    0.94
    $_{
    0.90
     $_{\
    0.88
     }_{\
    0.88
    ₀
    0.88
    _{{\
    0.87
     }_{
    0.86
    Act Density 0.099%

    No Known Activations