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

    Neuronpedia

    INDEX
    Explanations

    context. rules. complexities. instability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exclusive
    0.51
    b
    0.51
    ed
    0.46
     கட
    0.45
    d
    0.44
     glimps
    0.44
     annihilated
    0.44
    am
    0.43
     bizarre
    0.43
    bew
    0.43
    POSITIVE LOGITS
     SCAN
    0.50
     reduc
    0.46
    Killer
    0.45
     alleles
    0.45
    ClF
    0.45
    .$,
    0.45
    illance
    0.45
    Pin
    0.44
    険
    0.43
     asesin
    0.43
    Act Density 0.000%

    No Known Activations