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

    Neuronpedia

    INDEX
    Explanations

    turn off distractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zprac
    0.68
     ஒப்பு
    0.68
    oration
    0.67
    统
    0.65
    ership
    0.64
     partenariat
    0.63
    ्यता
    0.63
     escuela
    0.62
    enia
    0.61
     takım
    0.60
    POSITIVE LOGITS
     happy
    0.63
    Ek
    0.61
    ларни
    0.57
     ni
    0.56
     Happy
    0.55
     don
    0.54
    Happy
    0.54
    Bach
    0.54
     log
    0.54
    Raised
    0.53
    Act Density 0.136%

    No Known Activations