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

    Neuronpedia

    INDEX
    Explanations

    Rambling text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpos
    -0.07
     painters
    -0.07
    子の
    -0.07
    ษายน
    -0.07
     exce
    -0.06
    izabeth
    -0.06
     pau
    -0.06
     applicant
    -0.06
    гляд
    -0.06
     ét
    -0.06
    POSITIVE LOGITS
    贫
    0.07
     readily
    0.07
    (fi
    0.07
    >Data
    0.07
     ADA
    0.07
     indices
    0.07
    )}"↵
    0.07
    Indices
    0.06
    ITER
    0.06
     Generic
    0.06
    Act Density 0.000%

    No Known Activations