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

    Neuronpedia

    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hadron
    0.26
     troughs
    0.25
     histogram
    0.24
     analogues
    0.23
     daemon
    0.23
     convolution
    0.23
     barrage
    0.23
     singularities
    0.22
     algorithms
    0.22
     bourgeois
    0.22
    POSITIVE LOGITS
    á
    0.26
        
    0.25
    í
    0.24
    А
    0.23
    Cuando
    0.23
    Công
    0.23
    <ul>
    0.22
     Hvis
    0.22
    ama
    0.22
     Само
    0.22
    Act Density 4.110%

    No Known Activations