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

    Neuronpedia

    INDEX
    Explanations

    better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crystals
    -0.07
     голови
    -0.07
    _BOOL
    -0.06
    ेखन
    -0.06
    ects
    -0.06
     liquids
    -0.06
     tenga
    -0.06
     lehet
    -0.06
     intense
    -0.06
     Nora
    -0.06
    POSITIVE LOGITS
     bas
    0.07
    Trip
    0.06
    Code
    0.06
     VIN
    0.06
    Visited
    0.06
     write
    0.06
    _Write
    0.06
    	insert
    0.06
    数量
    0.06
     elektron
    0.06
    Act Density 0.000%

    No Known Activations