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

    Neuronpedia

    INDEX
    Explanations

    lens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deputies
    -0.07
    Hour
    -0.07
    .Writer
    -0.07
    _trap
    -0.06
    _history
    -0.06
    _hit
    -0.06
    ighbor
    -0.06
    �
    -0.06
    pop
    -0.06
    _dead
    -0.06
    POSITIVE LOGITS
     lens
    0.13
     Lens
    0.11
     lenses
    0.11
    Lens
    0.08
     DS
    0.08
     prism
    0.07
    SE
    0.07
     sensing
    0.07
     Prism
    0.07
     tư
    0.07
    Act Density 0.004%

    No Known Activations