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

    Neuronpedia

    INDEX
    Explanations

    own research and due diligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reminisc
    0.42
     modulus
    0.42
     neural
    0.42
     curvature
    0.42
     shades
    0.40
     amplitudes
    0.40
     modulation
    0.40
     linear
    0.39
     murmur
    0.39
     hues
    0.38
    POSITIVE LOGITS
     researching
    1.46
     research
    1.41
     researched
    1.37
    research
    1.29
    RESEARCH
    1.24
     Research
    1.23
    Research
    1.23
     RESEARCH
    1.19
     pesquisa
    1.16
     araşt
    1.15
    Act Density 0.015%

    No Known Activations