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

    Neuronpedia

    INDEX
    Explanations

    option and set selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >')
    0.34
     यूरोप
    0.34
     rosto
    0.34
    இவர்
    0.34
     acredita
    0.33
     rodzaj
    0.33
    }$&
    0.32
    ánsito
    0.32
     conducir
    0.32
    िलासपुर
    0.32
    POSITIVE LOGITS
    Hochspringen
    0.38
     jumping
    0.36
     Перейти
    0.36
     scriptlevel
    0.36
     \
    0.34
     jump
    0.34
     you
    0.33
     Jump
    0.32
     какие
    0.32
    哪些
    0.32
    Act Density 0.001%

    No Known Activations