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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burger
    -0.07
    formatted
    -0.07
    _defined
    -0.07
    Airport
    -0.06
     desert
    -0.06
    Ster
    -0.06
     jewels
    -0.06
    Repeated
    -0.06
     stating
    -0.06
    _EXIST
    -0.06
    POSITIVE LOGITS
    іння
    0.06
     wykon
    0.06
    งาน
    0.06
     meydana
    0.06
     milestones
    0.06
     makes
    0.05
     leveled
    0.05
    wiąz
    0.05
     hend
    0.05
     proved
    0.05
    Act Density 0.010%

    No Known Activations