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

    Neuronpedia

    INDEX
    Explanations

    product model numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     morphisms
    0.74
     containers
    0.72
     trademarks
    0.70
     Talend
    0.69
     syntax
    0.69
     collectives
    0.68
     distribution
    0.67
     subgroups
    0.66
     hurt
    0.66
     semantics
    0.66
    POSITIVE LOGITS
    C
    0.82
    E
    0.81
    A
    0.79
    F
    0.78
    S
    0.77
    BT
    0.76
    B
    0.76
    WF
    0.75
    ct
    0.75
    Be
    0.74
    Act Density 0.029%

    No Known Activations