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

    Neuronpedia

    INDEX
    Explanations

    attending events, meetings, or activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.99
     unabhängig
    0.93
    ри
    0.90
    ре
    0.87
    它
    0.86
     auf
    0.84
     giocatori
    0.81
    ో
    0.81
    ва
    0.80
     essere
    0.80
    POSITIVE LOGITS
    n
    1.19
    A
    1.09
    ,
    1.01
    Attend
    0.93
     взя
    0.85
     Attend
    0.84
    to
    0.84
    inp
    0.83
    attended
    0.83
    x
    0.82
    Act Density 0.007%

    No Known Activations