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

    Neuronpedia

    INDEX
    Explanations

    desirability, advantageous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.77
    UnusedPrivate
    -0.67
    SequentialGroup
    -0.66
    Datuak
    -0.66
    findpost
    -0.65
    ILayout
    -0.64
    WriteTagHelper
    -0.63
    awtextra
    -0.62
    ]")]
    -0.62
     nakalista
    -0.61
    POSITIVE LOGITS
    struktion
    0.52
     eccell
    0.47
    PathVariable
    0.46
    zí
    0.45
    aim
    0.44
     were
    0.44
    ือง
    0.43
     pousser
    0.42
    RELEASE
    0.42
    brates
    0.42
    Act Density 0.002%

    No Known Activations