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

    Neuronpedia

    INDEX
    Explanations

    handling case-insensitive input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bridge
    0.45
    oci
    0.43
    enable
    0.43
    OCI
    0.41
    oder
    0.41
    construct
    0.40
    SI
    0.40
    rcl
    0.40
    pecu
    0.39
    eni
    0.39
    POSITIVE LOGITS
    절
    0.40
     Kristin
    0.40
    獵
    0.39
    戦
    0.38
    セル
    0.38
     flotte
    0.37
     undone
    0.37
     flo
    0.37
     dressed
    0.37
     float
    0.36
    Act Density 0.000%

    No Known Activations