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

    Neuronpedia

    INDEX
    Explanations

    studios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Studios
    -0.84
     studios
    -0.79
    Studios
    -0.63
    studios
    -0.57
    usercontent
    -0.56
    setContentView
    -0.52
    kloped
    -0.51
     referrerpolicy
    -0.48
    ()))
    -0.47
    ]]
    -0.47
    POSITIVE LOGITS
    uté
    0.62
    ubscribe
    0.58
    eridge
    0.56
    redient
    0.56
     Gita
    0.56
    oire
    0.55
     reft
    0.55
     publicités
    0.54
     deberes
    0.54
     attiv
    0.54
    Act Density 0.659%

    No Known Activations