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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    diameter
    -1.22
     diameter
    -1.11
     Diameter
    -1.06
     generates
    -0.98
    generating
    -0.98
     générer
    -0.95
     Generating
    -0.94
    Diameter
    -0.94
     generate
    -0.94
     generating
    -0.92
    POSITIVE LOGITS
     from
    0.68
     all
    0.56
     and
    0.51
     a
    0.50
     what
    0.49
     la
    0.49
     at
    0.49
     one
    0.49
    DataMember
    0.49
     none
    0.48
    Act Density 0.057%

    No Known Activations