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

    Neuronpedia

    INDEX
    Explanations

    Crisis Text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doctorate
    0.86
     today
    0.75
    Brick
    0.73
    today
    0.72
    ELI
    0.72
    今天要
    0.70
     LTP
    0.69
    thesis
    0.69
     Doctorate
    0.68
    caster
    0.68
    POSITIVE LOGITS
     przech
    0.69
    льным
    0.69
     रेखा
    0.69
     яким
    0.69
     berakhir
    0.68
     તેને
    0.66
     ним
    0.66
     ří
    0.66
     आहार
    0.66
    時の
    0.64
    Act Density 0.008%

    No Known Activations