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

    Neuronpedia

    INDEX
    Explanations

    tracking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ひとり
    -0.08
    👐
    -0.07
     Adler
    -0.07
    ｟
    -0.07
     Appe
    -0.07
    plane
    -0.06
    CLEAR
    -0.06
    婉
    -0.06
     persönlich
    -0.06
     Goldberg
    -0.06
    POSITIVE LOGITS
     região
    0.07
    大幅提升
    0.07
     Court
    0.07
    严厉打击
    0.07
     Clem
    0.06
    View
    0.06
    altura
    0.06
    argar
    0.06
    ᴋ
    0.06
    -Jul
    0.06
    Act Density 0.025%

    No Known Activations