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

    Neuronpedia

    INDEX
    Explanations

    scout or ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ❑
    -0.08
    -demo
    -0.07
    _NON
    -0.07
    Process
    -0.07
    (depend
    -0.07
    (level
    -0.07
     völl
    -0.07
    _BATCH
    -0.06
     Bonus
    -0.06
    illions
    -0.06
    POSITIVE LOGITS
    oga
    0.07
    ogie
    0.07
     gear
    0.07
     preserved
    0.07
     toile
    0.07
    ritable
    0.07
     lowered
    0.06
    合唱
    0.06
    芟
    0.06
     patrol
    0.06
    Act Density 0.023%

    No Known Activations