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

    Neuronpedia

    INDEX
    Explanations

    graphics and hardware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phase
    1.05
     phases
    1.04
    phases
    0.98
     fase
    0.97
     période
    0.95
     périodes
    0.93
     PHASE
    0.93
    Phase
    0.93
     Phases
    0.91
     období
    0.89
    POSITIVE LOGITS
    istoire
    0.44
     multiv
    0.40
     Vertex
    0.39
     સર
    0.37
    td
    0.36
     tin
    0.36
     Mund
    0.34
    vl
    0.34
    𝕣
    0.34
     குர
    0.34
    Act Density 0.010%

    No Known Activations