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

    Neuronpedia

    INDEX
    Explanations

    linked to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.54
    нг
    0.45
    Chord
    0.45
    s
    0.45
    counter
    0.44
    isTrack
    0.44
    Compiler
    0.43
    Monitoring
    0.43
    Derivative
    0.43
    illustrated
    0.43
    POSITIVE LOGITS
     antigens
    0.54
    𝓪
    0.53
     kiddos
    0.52
     amenities
    0.52
     residues
    0.52
     habitats
    0.52
     isotopes
    0.52
     tunnels
    0.51
     sk
    0.50
     nitrates
    0.48
    Act Density 0.000%

    No Known Activations