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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ports
    -0.08
    iration
    -0.07
    -two
    -0.07
    >&
    -0.07
     patterns
    -0.07
    Health
    -0.07
     Battalion
    -0.07
     Raise
    -0.06
    _PUBLIC
    -0.06
     iki
    -0.06
    POSITIVE LOGITS
    ektiv
    0.07
     확실
    0.06
     أر
    0.06
    0.06
    「
    0.06
    모
    0.06
     multicast
    0.06
    lim
    0.06
     Lars
    0.06
     Bast
    0.06
    Act Density 0.076%

    No Known Activations