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

    Neuronpedia

    INDEX
    Explanations

    transition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ITEMS
    -0.07
    spir
    -0.07
    ombre
    -0.07
    кие
    -0.07
     xor
    -0.06
    ISTIC
    -0.06
    綠
    -0.06
    โปร
    -0.06
    본
    -0.06
     Innovative
    -0.06
    POSITIVE LOGITS
     fundament
    0.08
     relative
    0.07
    -"
    0.07
    Rank
    0.07
    sław
    0.07
    Ә
    0.07
     usernames
    0.07
    હ
    0.07
    ባ
    0.06
     Ministers
    0.06
    Act Density 0.002%

    No Known Activations