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

    Neuronpedia

    INDEX
    Explanations

    physical attributes and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indicators
    0.59
     in
    0.47
     assessments
    0.46
     actin
    0.46
     organisms
    0.45
     campaigns
    0.45
     organism
    0.44
     accounts
    0.43
     hypertrophy
    0.42
     campaign
    0.41
    POSITIVE LOGITS
    などは
    0.54
     parlé
    0.52
    などが
    0.51
     personnalisé
    0.50
    なども
    0.50
     TouchUtils
    0.49
    ꞎ
    0.49
     pourront
    0.48
     srebr
    0.47
    などを
    0.47
    Act Density 0.003%

    No Known Activations