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

    Neuronpedia

    INDEX
    Explanations

    asking for alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fino
    0.55
     CFU
    0.50
     fint
    0.49
    ትን
    0.47
     zicht
    0.46
     giallo
    0.46
     Mittag
    0.46
     KUR
    0.46
     compteur
    0.45
     Riemann
    0.45
    POSITIVE LOGITS
    aczego
    0.47
    神
    0.46
    have
    0.45
    illos
    0.44
    Seeing
    0.44
    ra
    0.44
    ędzie
    0.43
    ies
    0.43
    anners
    0.43
    amise
    0.43
    Act Density 0.006%

    No Known Activations