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

    Neuronpedia

    INDEX
    Explanations

    variations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     river
    -0.08
     стало
    -0.07
     Letters
    -0.07
    -world
    -0.07
    -factor
    -0.06
     fractures
    -0.06
    Tex
    -0.06
     Naval
    -0.06
     threw
    -0.06
    ilerinin
    -0.06
    POSITIVE LOGITS
    egasus
    0.07
     yolc
    0.07
    (outputs
    0.07
    nění
    0.06
     позволя
    0.06
     sentiment
    0.06
     پس
    0.06
    任务
    0.06
    俄
    0.06
     bluetooth
    0.06
    Act Density 0.014%

    No Known Activations