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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CARD
    -0.07
     underworld
    -0.06
     Gael
    -0.06
     créd
    -0.06
    ϑ
    -0.06
    Ini
    -0.06
     qualitative
    -0.06
    Orth
    -0.06
    	ps
    -0.06
    .filePath
    -0.06
    POSITIVE LOGITS
    2
    0.09
    3
    0.09
    6
    0.08
    5
    0.08
    -address
    0.07
     Launch
    0.07
    1
    0.07
    4
    0.07
     llevar
    0.07
     like
    0.07
    Act Density 21.507%

    No Known Activations