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

    Neuronpedia

    INDEX
    Explanations

    conditional logic and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TGFuZ
    0.53
    Aile
    0.49
     المياه
    0.48
    lasan
    0.46
     victorias
    0.46
     Deloitte
    0.45
     offent
    0.45
     appetizers
    0.44
     العديد
    0.44
     entretenimiento
    0.44
    POSITIVE LOGITS
     equations
    0.58
    if
    0.49
     iff
    0.49
    Then
    0.46
     depressing
    0.46
     eqn
    0.46
    ifdef
    0.46
     if
    0.45
    expr
    0.45
     Then
    0.45
    Act Density 0.008%

    No Known Activations