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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     logits
    -0.07
    tools
    -0.07
    Construct
    -0.07
     crystall
    -0.07
     pottery
    -0.07
     oluşturul
    -0.06
    寶
    -0.06
    ȹ
    -0.06
    [T
    -0.06
    POSITIVE LOGITS
    Af
    0.07
    ież
    0.07
    _assignment
    0.07
    _song
    0.06
     strides
    0.06
     Ż
    0.06
    -quarters
    0.06
    -per
    0.06
     Ved
    0.06
    مستثمر
    0.06
    Act Density 0.005%

    No Known Activations