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

    Neuronpedia

    INDEX
    Explanations

    as of today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    French
    0.50
    colnames
    0.49
    Success
    0.48
    El
    0.45
    Security
    0.44
    Secret
    0.44
    Rein
    0.44
    క
    0.44
     হইতেই
    0.42
     súa
    0.42
    POSITIVE LOGITS
     amidst
    0.66
     leveraging
    0.60
    ,.
    0.59
     aprox
    0.58
     overlooking
    0.58
     (~
    0.58
     circa
    0.58
     approx
    0.57
     nestled
    0.57
     whilst
    0.56
    Act Density 0.080%

    No Known Activations