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

    Neuronpedia

    INDEX
    Explanations

    larva

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pais
    -0.07
    (print
    -0.07
    }))↵↵
    -0.07
     эф
    -0.06
    endimento
    -0.06
     constitutes
    -0.06
    _cost
    -0.06
     ['#
    -0.06
     getopt
    -0.06
    .Pos
    -0.06
    POSITIVE LOGITS
     larvae
    0.10
     lar
    0.09
     markup
    0.07
     infancy
    0.07
     undergrad
    0.07
    -derived
    0.07
    bler
    0.07
     далі
    0.06
     lai
    0.06
    intersect
    0.06
    Act Density 0.003%

    No Known Activations