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

    Neuronpedia

    INDEX
    Explanations

    completing game tasks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narrower
    -0.07
    -stars
    -0.07
     otherwise
    -0.07
     Submission
    -0.07
    ptest
    -0.07
     /^(
    -0.06
    ूसर
    -0.06
    rray
    -0.06
    ücken
    -0.06
     бет
    -0.06
    POSITIVE LOGITS
    驗
    0.06
    _CD
    0.06
     notebook
    0.06
    _POP
    0.06
    .col
    0.06
     ป
    0.06
    ovation
    0.06
    Ant
    0.06
    첨부
    0.05
    ,)↵
    0.05
    Act Density 0.000%

    No Known Activations