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

    Neuronpedia

    INDEX
    Explanations

    Zenodo archives, DOIs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ा,
    -0.07
    wart
    -0.07
     RETURN
    -0.07
     vál
    -0.07
     conf
    -0.07
     cares
    -0.06
    umbs
    -0.06
    сь
    -0.06
    �
    -0.06
     ores
    -0.06
    POSITIVE LOGITS
    .central
    0.06
     inflicted
    0.06
    ='".
    0.06
     baseman
    0.06
    _G
    0.06
    _framework
    0.06
     lương
    0.06
    .section
    0.06
     WT
    0.06
     Záp
    0.06
    Act Density 0.006%

    No Known Activations