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

    Neuronpedia

    INDEX
    Explanations

    depending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gra
    -0.08
     Dob
    -0.08
     Sid
    -0.08
     GRE
    -0.08
    DEA
    -0.07
    Ago
    -0.07
     tether
    -0.07
    ASA
    -0.07
     tad
    -0.07
     odpr
    -0.07
    POSITIVE LOGITS
     circumstances
    0.12
     circumstance
    0.09
     circunstancias
    0.09
     엔
    0.08
    න
    0.08
    .Variable
    0.08
    有没有
    0.08
     circunst
    0.08
     реализации
    0.07
     اینکه
    0.07
    Act Density 0.034%

    No Known Activations