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

    Neuronpedia

    INDEX
    Explanations

    Computer language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ле
    -0.07
    Basically
    -0.07
    以及
    -0.07
     Purs
    -0.07
    _learn
    -0.07
    �
    -0.06
     mirac
    -0.06
    pixel
    -0.06
    есп
    -0.06
     Basically
    -0.06
    POSITIVE LOGITS
     ’
    0.06
     cat
    0.06
    .est
    0.06
    .numpy
    0.06
     wise
    0.06
     möchte
    0.06
     getX
    0.06
    .linkedin
    0.06
     Giving
    0.06
    engin
    0.06
    Act Density 0.000%

    No Known Activations