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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _math
    -0.06
     MRI
    -0.06
    рип
    -0.06
     avoidance
    -0.06
     accompanied
    -0.06
     researchers
    -0.06
    ‰
    -0.06
    ďte
    -0.06
     Canyon
    -0.06
    ьте
    -0.06
    POSITIVE LOGITS
    serter
    0.09
     diversified
    0.06
     Украї
    0.06
    收
    0.06
    etween
    0.06
    SOC
    0.06
     thigh
    0.06
    	↵	↵
    0.06
     budd
    0.06
     fh
    0.06
    Act Density 0.000%

    No Known Activations