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

    Neuronpedia

    INDEX
    Explanations

    code syntax assignments and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adoles
    0.94
    introdu
    0.93
    various
    0.93
    stabil
    0.91
    irrit
    0.90
    boots
    0.90
    the
    0.90
    healing
    0.89
    reflex
    0.89
    contemporary
    0.89
    POSITIVE LOGITS
     Some
    0.80
     json
    0.79
     util
    0.78
     Math
    0.78
     `${
    0.77
     self
    0.77
     $"{
    0.77
     JSON
    0.76
     Mathf
    0.76
     null
    0.74
    Act Density 0.467%

    No Known Activations