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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intensive
    -0.07
    ERY
    -0.07
     flames
    -0.07
     produces
    -0.06
     deceased
    -0.06
     karena
    -0.06
    ，还
    -0.06
    scenes
    -0.06
    ingroup
    -0.06
     randomNumber
    -0.06
    POSITIVE LOGITS
    .dsl
    0.07
    �
    0.07
     Knoxville
    0.07
     joystick
    0.07
     Altın
    0.06
     Vladimir
    0.06
    *\
    0.06
     playlist
    0.06
     прек
    0.06
     Australians
    0.06
    Act Density 0.145%

    No Known Activations