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

    Neuronpedia

    INDEX
    Explanations

    frequently target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gestaltung
    0.93
     earthly
    0.86
     žmog
    0.84
     cosmological
    0.84
     transcendent
    0.82
     metaphysical
    0.82
     admirer
    0.81
     metaphors
    0.81
    ിയെ
    0.79
    ҥ
    0.78
    POSITIVE LOGITS
     target
    2.24
     targets
    2.20
     targeting
    2.13
     targeted
    2.08
    target
    2.05
    Target
    2.02
     Target
    1.98
    targets
    1.95
    targeting
    1.94
     Targets
    1.93
    Act Density 0.125%

    No Known Activations