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

    Neuronpedia

    INDEX
    Explanations

    scientific analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üt
    -0.07
    _prime
    -0.07
    iful
    -0.07
     Selling
    -0.07
    bing
    -0.06
    blocking
    -0.06
    _IF
    -0.06
    _pairs
    -0.06
     Blocking
    -0.06
    кры
    -0.06
    POSITIVE LOGITS
    िसक
    0.07
    ･･
    0.06
    _Width
    0.06
    젠
    0.06
     sunglasses
    0.06
     sendMessage
    0.06
     [*
    0.06
    uni
    0.06
    _Inter
    0.06
    rete
    0.06
    Act Density 0.135%

    No Known Activations