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

    Neuronpedia

    INDEX
    Explanations

    How-to instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (),'
    -0.06
    owane
    -0.06
     Yup
    -0.06
     Afro
    -0.06
     Cooke
    -0.06
    rules
    -0.06
     Caf
    -0.06
     Clamp
    -0.06
     Obj
    -0.06
     mom
    -0.06
    POSITIVE LOGITS
    .Primary
    0.08
    ＞
    0.07
     ao
    0.07
    itate
    0.07
    оро
    0.06
    过
    0.06
    ΙΑΚ
    0.06
     undesirable
    0.06
    ρας
    0.06
    .business
    0.06
    Act Density 0.066%

    No Known Activations