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

    Neuronpedia

    INDEX
    Explanations

    grim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lancaster
    -0.07
     observed
    -0.07
     fly
    -0.07
    _repository
    -0.07
     enterprise
    -0.07
     брат
    -0.07
    阪
    -0.07
     Austr
    -0.06
    _examples
    -0.06
     experiencia
    -0.06
    POSITIVE LOGITS
     grim
    0.10
     dire
    0.10
     Dire
    0.09
     bleak
    0.08
     Grim
    0.08
    Dire
    0.07
     solemn
    0.07
     sober
    0.07
     위
    0.06
    dire
    0.06
    Act Density 0.007%

    No Known Activations