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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Interested
    -0.09
     interessado
    -0.09
     geïnteresseerd
    -0.08
     interessados
    -0.08
     interesado
    -0.08
     вист
    -0.08
     dịch
    -0.08
    -0.08
     ζ
    -0.07
    eseen
    -0.07
    POSITIVE LOGITS
    -only
    0.08
     wealth
    0.08
     jakarta
    0.08
     exemples
    0.08
    Example
    0.08
     ejemplo
    0.08
     Moi
    0.08
    xx
    0.07
    ತ್ವ
    0.07
     infinity
    0.07
    Act Density 0.043%
    No Known Activations