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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     three
    -0.06
     Three
    -0.06
    Six
    -0.06
     earnings
    -0.06
     neurological
    -0.06
     fuel
    -0.06
    Fuel
    -0.06
    OUN
    -0.06
    ują
    -0.06
     CURRENT
    -0.06
    POSITIVE LOGITS
    daemon
    0.07
    emiah
    0.07
    .ex
    0.07
    .mm
    0.06
    _prediction
    0.06
    _defs
    0.06
     LM
    0.06
     <>↵
    0.06
     {\↵
    0.06
    561
    0.06
    Act Density 0.046%

    No Known Activations