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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ژانویه
    -0.07
    ğına
    -0.06
     weaponry
    -0.06
    ubat
    -0.06
    یل
    -0.06
     UIT
    -0.06
    _multiplier
    -0.06
     Holder
    -0.06
     nghệ
    -0.06
     announce
    -0.06
    POSITIVE LOGITS
    ">'+
    0.07
     кім
    0.07
     ---------------------------------------------------------------------------↵
    0.06
    }}}
    0.06
     skilled
    0.06
     神
    0.06
     uninsured
    0.06
    .getApp
    0.06
    imately
    0.06
    .toJSON
    0.06
    Act Density 0.006%

    No Known Activations