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

    Neuronpedia

    INDEX
    Explanations

    by + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Risk
    0.55
    Ꮿ
    0.55
    ем
    0.55
    ет
    0.53
    Spell
    0.53
    CC
    0.52
    ной
    0.50
    Stabil
    0.50
    Education
    0.49
    Tolerance
    0.49
    POSITIVE LOGITS
    omatik
    0.46
     habitats
    0.43
     Humboldt
    0.42
     tsar
    0.42
     overturning
    0.42
    线程
    0.41
     habitat
    0.40
    ogie
    0.40
     rhubarb
    0.40
     Detecting
    0.40
    Act Density 0.001%

    No Known Activations