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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çevres
    -0.07
    -definition
    -0.06
    [(
    -0.06
     Aid
    -0.06
    ểm
    -0.06
     �
    -0.06
     ypos
    -0.05
    .Directory
    -0.05
     범
    -0.05
    -im
    -0.05
    POSITIVE LOGITS
     Andreas
    0.07
     amd
    0.07
     thought
    0.06
    ankind
    0.06
     readability
    0.06
     nephew
    0.06
    .visualization
    0.06
     Maven
    0.06
    _residual
    0.06
    roupe
    0.06
    Act Density 0.010%

    No Known Activations