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

    Neuronpedia

    INDEX
    Explanations

    out of bed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नवम्बर
    0.82
    boundary
    0.82
     सितम्बर
    0.82
     boundary
    0.81
    borderColor
    0.77
    ilebilir
    0.77
    BUF
    0.76
    "]]
    0.75
    ளவில்
    0.75
    newline
    0.73
    POSITIVE LOGITS
     bed
    0.93
     طریق
    0.83
     dodge
    0.82
     hiding
    0.81
     harms
    0.81
     sorts
    0.80
     commission
    0.79
     beds
    0.76
     envolvendo
    0.76
     dodging
    0.74
    Act Density 0.010%

    No Known Activations