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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     factory
    -0.08
     zdrav
    -0.07
     iktidar
    -0.07
    _usage
    -0.07
     loader
    -0.07
    ék
    -0.07
    ائل
    -0.07
     �
    -0.06
    try
    -0.06
    ое
    -0.06
    POSITIVE LOGITS
     §§
    0.07
     between
    0.07
     Jane
    0.06
    Jane
    0.06
    Forget
    0.06
    ––
    0.06
     Convert
    0.06
     Between
    0.06
    たちは
    0.06
     unused
    0.06
    Act Density 0.011%

    No Known Activations