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
    VC
    -0.07
     Cameron
    -0.07
    arım
    -0.07
    anni
    -0.07
     البحث
    -0.07
     Del
    -0.07
    INTER
    -0.07
    □
    -0.06
    DEX
    -0.06
    _num
    -0.06
    POSITIVE LOGITS
     remarkably
    0.06
     όταν
    0.06
     defaultCenter
    0.06
    rists
    0.06
    -нибудь
    0.06
    straints
    0.06
    ２０
    0.06
     strat
    0.06
    -books
    0.05
     Его
    0.05
    Act Density 0.003%

    No Known Activations