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

    Neuronpedia

    INDEX
    Explanations

    groups and partners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wind
    0.45
    कालय
    0.41
     postal
    0.40
     firearms
    0.40
     elem
    0.39
    Spatial
    0.38
    Postal
    0.38
    Copy
    0.38
    Une
    0.38
    Libraries
    0.38
    POSITIVE LOGITS
    rish
    0.41
     Bagh
    0.40
    ̇
    0.39
    tho
    0.37
     Schro
    0.37
     Simpl
    0.36
    >\<^
    0.36
    0.36
    apai
    0.36
    artoum
    0.36
    Act Density 0.000%

    No Known Activations