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

    Neuronpedia

    INDEX
    Explanations

    physics and mechanics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Engineering
    -0.07
     firefight
    -0.06
     Fram
    -0.06
     declares
    -0.06
     guar
    -0.06
     Hardy
    -0.06
    -Mart
    -0.06
     migli
    -0.06
    Scalars
    -0.06
     मण
    -0.06
    POSITIVE LOGITS
    _ACCOUNT
    0.06
    尼亚
    0.06
     徒歩
    0.06
     praying
    0.06
    _into
    0.06
    �
    0.06
    iglia
    0.06
     veterin
    0.06
    เคร
    0.06
     &'
    0.06
    Act Density 0.011%

    No Known Activations