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

    Neuronpedia

    INDEX
    Explanations

    vague

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .required
    -0.06
     ❤
    -0.06
     δο
    -0.06
    Instead
    -0.06
    下
    -0.06
     onward
    -0.06
    culate
    -0.06
    pras
    -0.06
    のに
    -0.06
    orative
    -0.06
    POSITIVE LOGITS
     vague
    0.17
     vaguely
    0.12
     universally
    0.07
     vag
    0.07
     uncertain
    0.07
     đài
    0.07
    ocode
    0.07
     throw
    0.07
    .scene
    0.07
     v
    0.07
    Act Density 0.011%

    No Known Activations