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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     신
    -0.06
     Snap
    -0.06
     nip
    -0.06
     go
    -0.06
     vistas
    -0.06
    ames
    -0.06
     mktime
    -0.06
     adlandır
    -0.06
    けど
    -0.06
    Uses
    -0.06
    POSITIVE LOGITS
    _FB
    0.07
    \":{\"
    0.06
    براير
    0.06
     TableRow
    0.06
     shed
    0.06
     contentious
    0.06
     Staples
    0.06
    (lock
    0.06
    IDAD
    0.06
    ظم
    0.06
    Act Density 0.011%

    No Known Activations