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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raster
    -0.08
    	virtual
    -0.07
    RPC
    -0.06
     rebels
    -0.06
     Roo
    -0.06
     AAA
    -0.06
     parser
    -0.06
     quot
    -0.06
    Jon
    -0.06
     超
    -0.06
    POSITIVE LOGITS
     payday
    0.07
     L
    0.07
    .core
    0.07
    овж
    0.06
    chet
    0.06
     loose
    0.06
    .arch
    0.06
    ρο
    0.06
    Checkpoint
    0.06
    （
    0.06
    Act Density 0.055%

    No Known Activations