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

    Neuronpedia

    INDEX
    Explanations

    encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ̈
    -0.07
    솔
    -0.07
    ARB
    -0.07
    レビ
    -0.07
    олош
    -0.07
     Mae
    -0.06
    ナル
    -0.06
    ağa
    -0.06
     erotici
    -0.06
    єш
    -0.06
    POSITIVE LOGITS
     Amateur
    0.07
     intersects
    0.06
     useful
    0.06
     ⌒
    0.06
    ável
    0.06
     herald
    0.06
    .getIn
    0.06
     allegation
    0.06
     apparent
    0.06
     reviewing
    0.06
    Act Density 0.000%

    No Known Activations