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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IM
    1.18
    /
    1.17
    वेलकम
    1.17
    关于
    1.15
    Further
    1.13
    “
    1.13
     海
    1.12
    OUG
    1.12
    /#
    1.11
     Federal
    1.09
    POSITIVE LOGITS
    ții
    1.24
    javab
    1.21
     ដែល
    1.06
    pliance
    1.05
    ęła
    1.05
     sinister
    1.03
    жь
    1.03
    adır
    1.02
     exorbit
    1.02
     rusting
    1.01
    Act Density 0.272%

    No Known Activations