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

    Neuronpedia

    INDEX
    Explanations

    loveisrespect resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     printing
    0.75
     green
    0.74
     recreation
    0.72
     printer
    0.70
     pleasure
    0.69
     ವ್ಯ
    0.68
     pretty
    0.68
     plein
    0.68
     game
    0.68
     gene
    0.67
    POSITIVE LOGITS
    Absolute
    0.78
    Rite
    0.78
    xas
    0.77
    NotExist
    0.76
    Ripe
    0.75
     нема
    0.75
    urangi
    0.74
    Std
    0.72
    totime
    0.71
    Voids
    0.70
    Act Density 0.002%

    No Known Activations