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

    Neuronpedia

    INDEX
    Explanations

    potentially using example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RE
    0.43
    ∈
    0.42
     【
    0.38
    まぁ
    0.37
    p
    0.37
    #!/
    0.37
    ানো
    0.36
    の
    0.36
    R
    0.36
    +
    0.36
    POSITIVE LOGITS
     وكذلك
    0.52
     craftsmen
    0.50
     suppuration
    0.47
     woodwork
    0.46
     ricerc
    0.45
     drzew
    0.44
     blacksmith
    0.44
    necks
    0.44
     barbers
    0.43
     provo
    0.43
    Act Density 0.005%

    No Known Activations