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

    Neuronpedia

    INDEX
    Explanations

    conjugate acid or base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あれ
    0.43
     Alberto
    0.40
    бовать
    0.40
     greasy
    0.39
    glia
    0.39
     업데이트
    0.39
     assunto
    0.39
    gimento
    0.39
     flav
    0.38
    )').
    0.38
    POSITIVE LOGITS
    yld
    0.38
    Suppress
    0.37
    Penn
    0.36
     DEJ
    0.36
     stopni
    0.36
    Repos
    0.35
     Cis
    0.35
    joke
    0.35
    Fruits
    0.35
    Teaching
    0.35
    Act Density 0.001%

    No Known Activations