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

    Neuronpedia

    INDEX
    Explanations

    hydro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TEM
    -0.08
    се
    -0.07
     autumn
    -0.06
     citt
    -0.06
     refute
    -0.06
    ozici
    -0.06
     quotation
    -0.06
     terrain
    -0.06
     locale
    -0.06
    oppel
    -0.06
    POSITIVE LOGITS
    Health
    0.07
     consolidation
    0.07
    (Http
    0.07
    ธน
    0.07
    /run
    0.07
    _do
    0.07
    ×↵↵
    0.06
    hong
    0.06
    abox
    0.06
     sclerosis
    0.06
    Act Density 0.003%

    No Known Activations