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

    Neuronpedia

    INDEX
    Explanations

    hidden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Province
    -0.07
    Compare
    -0.07
     SAX
    -0.06
    :%
    -0.06
    ouro
    -0.06
    atology
    -0.06
    ize
    -0.06
    Grade
    -0.06
     Brave
    -0.06
    .major
    -0.06
    POSITIVE LOGITS
     hidden
    0.16
     Hidden
    0.14
    -hidden
    0.10
    hidden
    0.10
    Hidden
    0.10
    (hidden
    0.09
    idden
    0.08
     hid
    0.08
    :hidden
    0.08
     frozen
    0.07
    Act Density 0.005%

    No Known Activations