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

    Neuronpedia

    INDEX
    Explanations

    gradually develop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()!=
    0.41
    atsioon
    0.40
    PTH
    0.39
    arns
    0.38
    rowadz
    0.37
    ✤
    0.36
    🎌
    0.36
    ój
    0.35
     Karriere
    0.35
     hebt
    0.35
    POSITIVE LOGITS
     influenza
    0.45
     terletak
    0.40
    รา
    0.39
     Influenza
    0.39
     ponctués
    0.38
     Mél
    0.38
     guiclass
    0.38
     expanding
    0.36
     ら
    0.36
    rary
    0.36
    Act Density 0.000%

    No Known Activations