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

    Neuronpedia

    INDEX
    Explanations

    Uncovering mystery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Him
    -0.07
     경찰
    -0.06
    iento
    -0.06
     днів
    -0.06
     communities
    -0.06
     threads
    -0.06
     Pir
    -0.06
    hur
    -0.06
     Tian
    -0.06
    pp
    -0.06
    POSITIVE LOGITS
     ditch
    0.07
    -under
    0.06
    -mile
    0.06
     initWith
    0.06
     guessing
    0.06
     कट
    0.06
     stringWith
    0.06
     Serena
    0.06
    _pitch
    0.06
    toggleClass
    0.06
    Act Density 0.043%

    No Known Activations