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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pense
    -0.07
    骨
    -0.06
     keras
    -0.06
    _FIN
    -0.06
     Luck
    -0.06
     Pretty
    -0.06
    _procs
    -0.06
     sono
    -0.06
     beef
    -0.06
     avoir
    -0.06
    POSITIVE LOGITS
    scrollView
    0.07
    fts
    0.07
     november
    0.06
    dg
    0.06
    heel
    0.06
     вещества
    0.06
     represented
    0.06
    +"<
    0.06
    /XMLSchema
    0.06
    σματα
    0.06
    Act Density 0.688%

    No Known Activations