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

    Neuronpedia

    INDEX
    Explanations

    bee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PEnd
    -0.07
    Basically
    -0.06
    ocaly
    -0.06
    Lv
    -0.06
    ُم
    -0.06
    距离
    -0.06
    �
    -0.06
     Basically
    -0.06
     pragma
    -0.06
    ों,
    -0.06
    POSITIVE LOGITS
     revision
    0.07
     costumes
    0.06
    (stmt
    0.06
     evaluations
    0.06
    "){↵
    0.06
     defend
    0.06
     photographs
    0.06
     accommodation
    0.06
    img
    0.06
     enraged
    0.06
    Act Density 0.000%

    No Known Activations