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

    Neuronpedia

    INDEX
    Explanations

    plan and phone senses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]];
    0.44
    㒵
    0.41
    ἆ
    0.40
    麃
    0.40
     የእ
    0.40
     اخذت
    0.39
     Tiểu
    0.39
     Augsburg
    0.38
    Despatx
    0.38
     аутох
    0.38
    POSITIVE LOGITS
     hammer
    0.68
     hammers
    0.54
     hammered
    0.54
    Hammer
    0.51
     Hammer
    0.49
     hammering
    0.46
    hammer
    0.41
     materials
    0.40
     gui
    0.40
    ”,
    0.39
    Act Density 0.000%

    No Known Activations