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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Მ
    0.41
     kader
    0.41
    hyde
    0.39
     sawtooth
    0.38
     orchards
    0.37
    orda
    0.37
    ాయని
    0.37
     PEAR
    0.37
    ោធ
    0.36
    ̰
    0.36
    POSITIVE LOGITS
    assistance
    0.37
    golf
    0.37
     தங்க
    0.36
     ට
    0.36
     Daily
    0.36
     लेखन
    0.35
     Fleming
    0.34
     didn
    0.34
     डू
    0.34
    irut
    0.34
    Act Density 0.000%

    No Known Activations