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

    Neuronpedia

    INDEX
    Explanations

    ities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cars
    -0.07
     Erik
    -0.06
     washer
    -0.06
    есто
    -0.06
     Yo
    -0.06
     Hum
    -0.06
     rast
    -0.06
     Rust
    -0.06
    /dom
    -0.06
    ransition
    -0.06
    POSITIVE LOGITS
    _MONTH
    0.07
     resolving
    0.07
     newcomers
    0.06
    Magnitude
    0.06
    зації
    0.06
    xEB
    0.06
    Salvar
    0.06
     unwanted
    0.06
     instrumentation
    0.06
     Generator
    0.06
    Act Density 0.000%

    No Known Activations