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

    Neuronpedia

    INDEX
    Explanations

    Construct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sea
    -0.07
    neği
    -0.07
     bacteria
    -0.06
     analý
    -0.06
     bag
    -0.06
     differences
    -0.06
     peptide
    -0.06
     personalize
    -0.06
     männer
    -0.06
    727
    -0.06
    POSITIVE LOGITS
     constructing
    0.10
     constructed
    0.09
     Components
    0.08
     Constructors
    0.08
    Constructor
    0.08
    constructed
    0.08
     construct
    0.08
    Construction
    0.08
     constructs
    0.08
    Constructed
    0.08
    Act Density 0.026%

    No Known Activations