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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hesap
    -0.07
     pravděpodob
    -0.07
    iag
    -0.07
     antiqu
    -0.07
    serir
    -0.06
    幾
    -0.06
     hayvan
    -0.06
    оке
    -0.06
    ickém
    -0.06
    agem
    -0.06
    POSITIVE LOGITS
    recv
    0.07
     Fransa
    0.07
    d
    0.07
    j
    0.07
    Hol
    0.06
     Mobility
    0.06
    -D
    0.06
     d
    0.06
     differ
    0.06
    eyed
    0.06
    Act Density 0.001%

    No Known Activations