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

    Neuronpedia

    INDEX
    Explanations

    definition, dialect, achieved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    row
    0.44
     ketemu
    0.42
     matéria
    0.40
     delito
    0.40
     ^=
    0.39
    ru
    0.39
     fh
    0.39
     Markdown
    0.39
     fuit
    0.38
     cw
    0.38
    POSITIVE LOGITS
    競技
    0.51
    ה
    0.50
    場
    0.49
    ار
    0.49
    यंस
    0.48
    টি
    0.48
     figurines
    0.47
     場
    0.46
    ף
    0.46
     पुरुष
    0.46
    Act Density 0.000%

    No Known Activations