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

    Neuronpedia

    INDEX
    Explanations

    path separators and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Epilepsy
    0.31
     Lupus
    0.28
     Hurricane
    0.27
     Epoxy
    0.27
     Cyst
    0.27
     Asthma
    0.27
     Chủ
    0.26
     PTSD
    0.26
     Artillery
    0.26
     Testosterone
    0.26
    POSITIVE LOGITS
    _
    0.53
    /
    0.50
    -
    0.43
    ://
    0.40
    .
    0.39
    \_
    0.39
    info
    0.38
    ize
    0.38
    agem
    0.37
    zinha
    0.37
    Act Density 0.339%

    No Known Activations