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

    Neuronpedia

    INDEX
    Explanations

    css properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nebude
    0.77
    J
    0.75
    Use
    0.74
    S
    0.74
    Find
    0.71
    ერ
    0.68
    ఎ
    0.68
    May
    0.67
    V
    0.67
    Ann
    0.67
    POSITIVE LOGITS
     contemporary
    1.04
     Fellow
    0.98
     charismatic
    0.97
     Frege
    0.97
    <unused765>
    0.96
    DWARF
    0.94
     Shaping
    0.94
    <unused557>
    0.93
     Fractal
    0.93
     ومن
    0.93
    Act Density 0.421%

    No Known Activations