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

    Neuronpedia

    INDEX
    Explanations

    configuration settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stderr
    0.38
     UINT
    0.38
    stdin
    0.37
    ()])
    0.37
    SuccessListener
    0.37
     eigenvalues
    0.36
    Spectrum
    0.36
     отношении
    0.36
     guna
    0.36
    াধীন
    0.35
    POSITIVE LOGITS
     goes
    0.55
     below
    0.54
     должны
    0.54
     هنا
    0.51
     here
    0.50
    goes
    0.49
     abaixo
    0.49
     повинні
    0.49
     begins
    0.48
     должна
    0.48
    Act Density 0.004%

    No Known Activations