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

    Neuronpedia

    INDEX
    Explanations

    legal violations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cont
    -0.07
     Chu
    -0.07
     borr
    -0.07
     haute
    -0.07
    -fw
    -0.07
     oğlu
    -0.07
     又
    -0.07
     warp
    -0.06
     örg
    -0.06
     FW
    -0.06
    POSITIVE LOGITS
    *&
    0.06
     favors
    0.06
    лятор
    0.06
    much
    0.06
    érience
    0.06
     cumpl
    0.06
     washington
    0.06
    .&
    0.06
    ails
    0.06
    ...(
    0.06
    Act Density 0.054%

    No Known Activations