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

    Neuronpedia

    INDEX
    Explanations

    introducing a subject or point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ranges
    0.45
    ]*
    0.42
    )\
    0.41
    ]
    0.40
     occupying
    0.40
    Chest
    0.40
     belated
    0.40
    Oper
    0.39
    Invalid
    0.38
     precedence
    0.38
    POSITIVE LOGITS
    touchstart
    0.45
    gine
    0.41
     ’’
    0.40
     kttt
    0.40
    និយាយ
    0.40
    🗨
    0.40
    ntz
    0.39
     kulttu
    0.39
     gemeins
    0.38
    किया
    0.38
    Act Density 0.001%

    No Known Activations