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

    Neuronpedia

    INDEX
    Explanations

    synaptic plasticity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hickory
    0.42
     espace
    0.40
    жет
    0.39
     Hacienda
    0.39
    Soda
    0.38
     régions
    0.38
    LAG
    0.38
     Liebe
    0.38
    CMake
    0.38
     Cinta
    0.37
    POSITIVE LOGITS
    unchecked
    0.60
     unchecked
    0.57
     suppressed
    0.47
     suppress
    0.46
     unfair
    0.46
     resource
    0.45
     pushing
    0.41
     checked
    0.41
     endlessly
    0.41
     suppressing
    0.40
    Act Density 0.000%

    No Known Activations