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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monsters
    -0.09
     monstru
    -0.08
    (parameter
    -0.07
     buy
    -0.07
     observational
    -0.07
    (term
    -0.07
     amazing
    -0.07
     regional
    -0.07
     guardians
    -0.07
     қорға
    -0.07
    POSITIVE LOGITS
    영
    0.08
    -я
    0.08
     dedicate
    0.08
    း
    0.08
     смогут
    0.08
     sunny
    0.08
    _frames
    0.07
     Totally
    0.07
    Frames
    0.07
    -operated
    0.07
    Act Density 0.002%

    No Known Activations