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

    Neuronpedia

    INDEX
    Explanations

    pilgrims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     свого
    -0.07
     tensors
    -0.06
     sich
    -0.06
    这个
    -0.06
     cinematic
    -0.06
     Canyon
    -0.06
     定
    -0.06
     discarded
    -0.05
     tộc
    -0.05
     :/:
    -0.05
    POSITIVE LOGITS
    grim
    0.14
     Pil
    0.12
    ims
    0.10
     pilgr
    0.10
     Plymouth
    0.10
    gr
    0.08
    -Ray
    0.07
    _PERCENT
    0.07
    ğa
    0.07
    pressor
    0.07
    Act Density 0.005%

    No Known Activations