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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phản
    -0.07
    forcer
    -0.06
    <>(
    -0.06
    ilder
    -0.06
     opin
    -0.06
     ovliv
    -0.06
    _billing
    -0.06
    Anna
    -0.06
    °N
    -0.06
    atus
    -0.06
    POSITIVE LOGITS
    Número
    0.06
     curtains
    0.06
     Charles
    0.06
    inc
    0.06
     beta
    0.06
     클
    0.06
     several
    0.06
    ELSE
    0.06
     (?
    0.06
     BigInt
    0.06
    Act Density 0.000%

    No Known Activations