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

    Neuronpedia

    INDEX
    Explanations

    context and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coding
    0.44
     Friday
    0.44
     egress
    0.42
    indices
    0.41
    in
    0.41
    ```
    0.41
    inc
    0.41
    j
    0.40
    cott
    0.39
    ally
    0.39
    POSITIVE LOGITS
     offrire
    0.46
     delito
    0.46
    猊
    0.44
     cuantit
    0.44
     gambler
    0.44
    ILER
    0.42
     Beziehung
    0.41
     juggle
    0.41
    繧
    0.41
    фы
    0.41
    Act Density 0.000%

    No Known Activations