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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Titles
    -0.07
     tubes
    -0.07
    ="""
    -0.07
     Matter
    -0.06
     creepy
    -0.06
     doubt
    -0.06
     standalone
    -0.06
    Schedule
    -0.06
     Hal
    -0.06
    번째
    -0.06
    POSITIVE LOGITS
     Flint
    0.06
     квіт
    0.06
    пат
    0.06
    �
    0.06
     Burlington
    0.06
     practise
    0.06
    .backend
    0.06
    racial
    0.06
    DET
    0.06
    /bit
    0.06
    Act Density 0.024%

    No Known Activations