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

    Neuronpedia

    INDEX
    Explanations

    crisis support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verste
    0.70
     curiosity
    0.68
     surety
    0.67
    ின
    0.67
    荤
    0.66
    acci
    0.65
     แยก
    0.62
    成り
    0.61
    เหลือ
    0.61
    uml
    0.61
    POSITIVE LOGITS
     Mut
    0.95
    Mut
    0.90
    mut
    0.80
    Jos
    0.80
    Kos
    0.77
    Muse
    0.73
     Mu
    0.73
    LIS
    0.70
     Muse
    0.70
    Lis
    0.69
    Act Density 0.059%

    No Known Activations