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

    Neuronpedia

    INDEX
    Explanations

    Ripple, stream, medium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    나
    1.13
    ic
    0.98
    id
    0.94
    J
    0.92
    at
    0.92
    ak
    0.89
    us
    0.88
    라
    0.88
    2
    0.88
    os
    0.87
    POSITIVE LOGITS
    మన్
    0.94
    𝙀
    0.91
    గం
    0.84
     heps
    0.79
     און
    0.79
     terraza
    0.79
     manpower
    0.77
     Eben
    0.77
     grievance
    0.77
     primaryStage
    0.76
    Act Density 0.001%

    No Known Activations