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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manglid
    0.49
     surgeons
    0.44
     sovereigns
    0.41
     freedoms
    0.41
     palaces
    0.40
    стях
    0.40
     monsters
    0.40
     psychiatrists
    0.40
     ceilings
    0.39
     comedies
    0.39
    POSITIVE LOGITS
    info
    0.47
    <0xE3>
    0.40
    同
    0.39
     इच्छुक
    0.38
    いの
    0.38
    oretically
    0.38
    ("
    0.37
    source
    0.36
    history
    0.36
     또는
    0.36
    Act Density 0.002%

    No Known Activations