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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fl
    -0.07
     extended
    -0.07
    _extended
    -0.07
    _processor
    -0.07
     the
    -0.07
     fatalities
    -0.07
     Matthias
    -0.07
     marks
    -0.06
    幅
    -0.06
     movement
    -0.06
    POSITIVE LOGITS
    _ALREADY
    0.16
    Existing
    0.15
    _existing
    0.14
     existente
    0.13
     Existing
    0.13
    existing
    0.13
    Already
    0.12
     existentes
    0.12
     ఇప్పటికే
    0.12
     vorhand
    0.12
    Act Density 0.020%

    No Known Activations