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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     is
    -0.07
    skills
    -0.06
    _pointer
    -0.06
     relates
    -0.06
     are
    -0.06
    -options
    -0.06
     FN
    -0.06
    -option
    -0.06
    struments
    -0.06
     velocities
    -0.06
    POSITIVE LOGITS
    rika
    0.07
    ковые
    0.07
     Markus
    0.07
    Few
    0.06
    _cons
    0.06
    Similarly
    0.06
     personalize
    0.06
    ERG
    0.06
     Tony
    0.06
    _BOUND
    0.06
    Act Density 0.070%

    No Known Activations