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

    Neuronpedia

    INDEX
    Explanations

    punctuation, common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hir
    -0.07
     checklist
    -0.07
    وبی
    -0.07
    “As
    -0.07
    كور
    -0.06
    according
    -0.06
     گاه
    -0.06
    _partner
    -0.06
     Inspection
    -0.06
     absor
    -0.06
    POSITIVE LOGITS
     nth
    0.07
     Xã
    0.07
     prés
    0.06
     emojis
    0.06
     내려
    0.06
    istency
    0.06
    xlim
    0.06
     converged
    0.06
     Tmax
    0.06
    ảm
    0.06
    Act Density 0.071%

    No Known Activations