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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    animate
    -0.07
    _wc
    -0.07
    -feedback
    -0.07
    _conf
    -0.07
     Quarterly
    -0.07
     Relationships
    -0.07
    -highlight
    -0.07
     Özellikle
    -0.07
    noon
    -0.07
    _package
    -0.07
    POSITIVE LOGITS
     hurts
    0.06
    Flat
    0.06
     tweeted
    0.06
    nik
    0.05
     akka
    0.05
    utin
    0.05
    ）
    0.05
     указ
    0.05
    otate
    0.05
     �
    0.05
    Act Density 0.009%

    No Known Activations