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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    persist
    -0.07
    isValid
    -0.07
    隔离
    -0.07
     getDefault
    -0.07
    anity
    -0.06
     المواطن
    -0.06
     reassure
    -0.06
    iene
    -0.06
    eiß
    -0.06
     ticks
    -0.06
    POSITIVE LOGITS
     Memor
    0.07
     Coh
    0.07
    ᵈ
    0.07
    บท
    0.07
    Quite
    0.07
    日凌晨
    0.07
    (note
    0.06
     cope
    0.06
     Corp
    0.06
     Leon
    0.06
    Act Density 0.003%

    No Known Activations