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

    Neuronpedia

    INDEX
    Explanations

    technical subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.42
    ۲
    0.39
    isle
    0.38
    igi
    0.38
    IGA
    0.38
    alla
    0.38
     उक्त
    0.38
    riting
    0.37
    iento
    0.37
    chent
    0.37
    POSITIVE LOGITS
     grasses
    0.40
     relatable
    0.39
    看似
    0.37
    ជ្រ
    0.37
     percep
    0.37
     unavailable
    0.36
     hovered
    0.36
    视角
    0.36
    後半
    0.36
     ठ
    0.35
    Act Density 0.009%

    No Known Activations