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

    Neuronpedia

    INDEX
    Explanations

    recursion depth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
        
    0.74
    ↵
    0.71
         
    0.64
    i
    0.63
    if
    0.57
    import
    0.57
    आई
    0.57
    ıc
    0.57
     informó
    0.56
    s
    0.55
    POSITIVE LOGITS
     hydroly
    0.67
     thermodynam
    0.64
     balsam
    0.64
     chemically
    0.64
     emuls
    0.63
    BleStatus
    0.62
     neutrophil
    0.62
     colloidal
    0.61
     sarcom
    0.61
    UnderWater
    0.60
    Act Density 0.304%

    No Known Activations