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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orient
    -0.07
    ’ai
    -0.07
     Pow
    -0.07
    REC
    -0.06
     Jonas
    -0.06
    'We
    -0.06
    งส
    -0.06
    :inline
    -0.06
    edited
    -0.06
    ]=='
    -0.06
    POSITIVE LOGITS
     interle
    0.07
     meltdown
    0.07
    牌
    0.07
    ynchronize
    0.07
    -family
    0.06
    amsung
    0.06
     Tamil
    0.06
     instantiate
    0.06
     choosing
    0.06
     arbitr
    0.06
    Act Density 0.000%

    No Known Activations