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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     konce
    -0.07
    まった
    -0.07
    val
    -0.07
    ователь
    -0.07
     blouse
    -0.07
    '=>'
    -0.06
    11
    -0.06
     softened
    -0.06
     araştırma
    -0.06
    하면서
    -0.06
    POSITIVE LOGITS
    공부
    0.06
    createElement
    0.06
     gratuita
    0.06
    Pooling
    0.06
     Comey
    0.06
     dati
    0.06
    ippet
    0.06
     常
    0.06
     existe
    0.06
     Gym
    0.06
    Act Density 0.192%

    No Known Activations