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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    галі
    -0.07
    řad
    -0.07
     #{
    -0.07
     (?
    -0.07
     mich
    -0.07
    ritis
    -0.07
     Allocation
    -0.06
     xl
    -0.06
     "{{
    -0.06
     lives
    -0.06
    POSITIVE LOGITS
     smoothing
    0.06
    磨
    0.06
     intoxicated
    0.06
     وغير
    0.06
     unpredictable
    0.06
    [next
    0.06
    Unlock
    0.06
    ouce
    0.06
    >";
    0.06
    _waiting
    0.05
    Act Density 0.231%

    No Known Activations