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

    Neuronpedia

    INDEX
    Explanations

    compound names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sauvignon
    0.72
     punitive
    0.68
     Pd
    0.68
     Uy
    0.68
     inhibitory
    0.67
     Giulia
    0.67
     sbParams
    0.67
     unequivocal
    0.65
     Bb
    0.65
     Underwater
    0.64
    POSITIVE LOGITS
    auth
    0.98
    net
    0.92
    box
    0.90
    comm
    0.89
    health
    0.88
    math
    0.87
    Auth
    0.86
    go
    0.85
    com
    0.85
    fi
    0.84
    Act Density 0.108%

    No Known Activations