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

    Neuronpedia

    INDEX
    Explanations

    central

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gun
    -0.07
    _sz
    -0.07
    jím
    -0.06
    ानम
    -0.06
     adequ
    -0.06
    λέ
    -0.06
     соот
    -0.06
    Sequential
    -0.06
    gebra
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     unbelievable
    0.07
     thunder
    0.07
    _FAIL
    0.07
     MISSING
    0.06
     merge
    0.06
     befind
    0.06
     mocks
    0.06
     Hollywood
    0.06
     harmful
    0.06
     Belg
    0.06
    Act Density 0.000%

    No Known Activations