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

    Neuronpedia

    INDEX
    Explanations

    specific examples or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Edwards
    0.46
     membentuk
    0.39
     proposte
    0.38
     kultur
    0.37
     läuft
    0.37
     Westminster
    0.36
     jeste
    0.36
     hänen
    0.36
     bliver
    0.35
     kimi
    0.35
    POSITIVE LOGITS
    Individual
    0.64
    individual
    0.61
     individuale
    0.57
     индивидуа
    0.52
     individual
    0.52
    单个
    0.52
     конкре
    0.48
     Individual
    0.48
    Specific
    0.47
    TextBox
    0.46
    Act Density 0.227%

    No Known Activations