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

    Neuronpedia

    INDEX
    Explanations

    coffee grounds or Python

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     temperature
    0.55
     manufacturer
    0.52
     denounce
    0.52
     sixth
    0.49
    {
    0.49
    此
    0.49
     höch
    0.47
     unthinkable
    0.47
     playground
    0.46
     revise
    0.45
    POSITIVE LOGITS
    ĝ
    0.49
    gaan
    0.48
    Ridge
    0.47
    jaan
    0.47
    Norton
    0.45
    Rig
    0.45
    Psal
    0.44
    ubwa
    0.43
    Mu
    0.43
     때문에
    0.43
    Act Density 0.004%

    No Known Activations