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

    Neuronpedia

    INDEX
    Explanations

    compound words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    клады
    0.52
     dissolve
    0.51
    ير
    0.50
     buckle
    0.50
     buckles
    0.49
     pouring
    0.48
     guía
    0.48
    اويه
    0.48
    iaxial
    0.47
     najwy
    0.46
    POSITIVE LOGITS
    i
    0.60
    u
    0.55
    e
    0.54
    o
    0.53
     Knowledge
    0.53
     Standards
    0.52
    -
    0.52
    jä
    0.51
    (
    0.50
     Threat
    0.48
    Act Density 0.000%

    No Known Activations