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

    Neuronpedia

    INDEX
    Explanations

    visual elements, specified number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deserial
    0.95
     clipboard
    0.89
     cbind
    0.89
     polynomial
    0.88
     verwenden
    0.88
    二维
    0.85
     textbox
    0.85
    MenuItem
    0.82
    してください
    0.81
     tmux
    0.81
    POSITIVE LOGITS
     mild
    0.89
    falls
    0.82
    чета
    0.82
     inexperienced
    0.80
    번에
    0.79
     co
    0.74
     flamb
    0.74
    bury
    0.73
     fiercely
    0.73
     tomo
    0.72
    Act Density 0.000%

    No Known Activations