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

    Neuronpedia

    INDEX
    Explanations

    VR, IP, energy, running

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caída
    0.39
     collectivités
    0.39
     jì
    0.37
     jinfo
    0.37
    When
    0.35
     ώστε
    0.35
    ˍ
    0.35
    ιβ
    0.35
    ージャー
    0.35
    গী
    0.35
    POSITIVE LOGITS
     relate
    0.39
     Именно
    0.37
    Dh
    0.37
     Norman
    0.37
    Scient
    0.37
     அல்லாஹ்
    0.37
    सनीय
    0.36
     Handsome
    0.36
    Currency
    0.36
    idence
    0.36
    Act Density 0.000%

    No Known Activations