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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingredient
    -0.07
     precision
    -0.06
    Selection
    -0.06
    venience
    -0.06
     mort
    -0.06
    _digest
    -0.06
     five
    -0.06
     mistaken
    -0.06
    phasis
    -0.06
    REDIENT
    -0.06
    POSITIVE LOGITS
     çeşit
    0.07
     onBindViewHolder
    0.07
     etkili
    0.07
     شامل
    0.06
    toHaveBeenCalledWith
    0.06
     Holden
    0.06
    .KeyCode
    0.06
    ेहर
    0.06
     denne
    0.06
    .ReLU
    0.06
    Act Density 0.009%

    No Known Activations