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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAIN
    -0.07
     believed
    -0.07
     Atlas
    -0.07
     Ap
    -0.06
     провести
    -0.06
    veys
    -0.06
    environments
    -0.06
    _iff
    -0.06
    hus
    -0.06
    яется
    -0.06
    POSITIVE LOGITS
    оген
    0.06
    ",-
    0.06
    verture
    0.06
     newText
    0.06
    iation
    0.06
     особливо
    0.06
    addir
    0.06
    _IV
    0.06
    <strong
    0.06
     possibly
    0.06
    Act Density 0.000%

    No Known Activations