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

    Neuronpedia

    INDEX
    Explanations

    in phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oretically
    0.21
    इसमें
    0.20
    things
    0.19
    oretical
    0.19
     इसमें
    0.19
    Concini
    0.18
     béné
    0.18
    在于
    0.18
     cheered
    0.18
     privind
    0.17
    POSITIVE LOGITS
     accordance
    0.50
     lieu
    0.42
     conjunction
    0.38
     tandem
    0.38
     order
    0.37
     terms
    0.37
     the
    0.36
     relation
    0.36
    lc
    0.36
    mediately
    0.34
    Act Density 0.161%

    No Known Activations