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

    Neuronpedia

    INDEX
    Explanations

    coordinates and City names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Opposition
    0.52
     Thumbnail
    0.49
     Далее
    0.48
    Critic
    0.47
     critics
    0.47
     in
    0.47
     Coronavirus
    0.46
    Logger
    0.46
     QT
    0.46
    s
    0.46
    POSITIVE LOGITS
    W
    0.56
    ർ
    0.53
     harina
    0.51
     uspe
    0.49
    SAND
    0.49
    пня
    0.49
    M
    0.48
    HAEL
    0.47
     melap
    0.46
     kanssa
    0.45
    Act Density 0.000%

    No Known Activations