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

    Neuronpedia

    INDEX
    Explanations

    set theory and zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .variables
    -0.08
     wild
    -0.08
     dill
    -0.07
     criteria
    -0.07
    Criteria
    -0.07
     oversized
    -0.07
     รี
    -0.07
     curse
    -0.07
    Expiry
    -0.07
     markets
    -0.07
    POSITIVE LOGITS
     Constructors
    0.09
     constructions
    0.09
     constructors
    0.08
     cum
    0.08
     constructed
    0.08
     bé
    0.08
    _Construct
    0.08
    erk
    0.08
    constructed
    0.08
    ostr
    0.07
    Act Density 0.005%

    No Known Activations