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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'y
    -0.07
     checkpoints
    -0.07
    Toy
    -0.07
    RGB
    -0.07
    Std
    -0.06
     checkpoint
    -0.06
    STS
    -0.06
    وى
    -0.06
    apture
    -0.06
    kerja
    -0.06
    POSITIVE LOGITS
     actionTypes
    0.07
    ाइम
    0.07
     Endpoint
    0.07
    ِر
    0.07
     POV
    0.06
     FAG
    0.06
    /{{$
    0.06
     Carbon
    0.06
     představ
    0.06
     CONTRACT
    0.06
    Act Density 0.026%

    No Known Activations