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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    酒
    -0.07
    iêm
    -0.07
    _INTER
    -0.07
    ูกค
    -0.07
     prostitute
    -0.06
    军
    -0.06
     lest
    -0.06
     PackageManager
    -0.06
    diğini
    -0.06
     внес
    -0.06
    POSITIVE LOGITS
    Signature
    0.07
    (fileName
    0.06
    operation
    0.06
     bully
    0.06
    /**
↵
    0.06
    ↵
↵
    0.06
     memorial
    0.06
     representations
    0.06
    ---
↵
    0.06
    	Console
    0.06
    Act Density 0.032%

    No Known Activations