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

    Neuronpedia

    INDEX
    Explanations

    controlling something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     忄
    1.09
    medallas
    1.05
    јединачна
    1.02
     Serrurier
    1.02
     راجس
    0.99
    冦
    0.98
    organizations
    0.98
    쇤
    0.98
     voisins
    0.97
    𝟘
    0.96
    POSITIVE LOGITS
    ä
    1.47
    .
    1.25
    ia
    1.16
     controlled
    1.16
    ih
    1.15
    -
    1.10
    uh
    1.05
    v
    1.02
    _
    1.02
    ت
    1.00
    Act Density 0.014%

    No Known Activations