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

    Neuronpedia

    INDEX
    Explanations

    list items or structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    何
    0.42
    Counts
    0.37
    ض
    0.36
    Still
    0.36
    Acknowled
    0.36
     appre
    0.36
    م
    0.34
    できない
    0.34
    제
    0.34
    й
    0.33
    POSITIVE LOGITS
    0.48
    </li>
    0.44
     **
    0.40
    ą
    0.39
     Flyers
    0.39
     Verhältnis
    0.39
     Մ
    0.38
    setWidth
    0.38
    ┆
    0.38
     Keychain
    0.38
    Act Density 0.095%

    No Known Activations