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

    Neuronpedia

    INDEX
    Explanations

    determine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TH
    -0.07
     wider
    -0.07
    -sem
    -0.06
     RAM
    -0.06
     ALT
    -0.06
    ition
    -0.06
     Baylor
    -0.06
     HB
    -0.06
     mistakes
    -0.06
     SIDE
    -0.06
    POSITIVE LOGITS
    歡
    0.07
    33
    0.07
    55
    0.07
     Trouble
    0.06
    ominated
    0.06
    ynamics
    0.06
    paired
    0.06
    ->{_
    0.06
    'nın
    0.06
    489
    0.06
    Act Density 0.000%

    No Known Activations