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

    Neuronpedia

    INDEX
    Explanations

    planets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mars
    -1.30
     mars
    -0.92
     Martian
    -0.92
    Mars
    -0.90
    mars
    -0.84
    os
    -0.78
     Saturn
    -0.77
     MARS
    -0.72
    IVEREF
    -0.71
     Marte
    -0.67
    POSITIVE LOGITS
    hawatir
    0.66
    Tikang
    0.52
     huom
    0.48
     atardecer
    0.47
    ثيق
    0.46
    noStroke
    0.45
     contemporáneo
    0.45
     digitalen
    0.44
     Majefty
    0.43
    zbęd
    0.43
    Act Density 0.116%

    No Known Activations