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

    Neuronpedia

    INDEX
    Explanations

    translation and development contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ale
    0.49
    ato
    0.49
    ila
    0.49
    ela
    0.49
    omie
    0.48
    ata
    0.46
    ina
    0.46
    дно
    0.46
    iel
    0.45
     کوډ
    0.44
    POSITIVE LOGITS
     phong
    0.50
     crystals
    0.49
    тиви
    0.49
     scars
    0.47
     breed
    0.47
     fifty
    0.47
     compensate
    0.47
     disperse
    0.47
     fragments
    0.47
     clair
    0.47
    Act Density 0.000%

    No Known Activations