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

    Neuronpedia

    INDEX
    Explanations

    potential issues and trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Accum
    0.48
    Youth
    0.46
    Guides
    0.44
     accumulation
    0.44
     apprenticeship
    0.44
    Gabriel
    0.43
    Guide
    0.43
    Solve
    0.42
    Gest
    0.41
    Chaos
    0.41
    POSITIVE LOGITS
     물
    0.59
     vatten
    0.53
     voda
    0.50
     Seiko
    0.49
     wasser
    0.48
     potrav
    0.48
     tuku
    0.48
    మ్యాచ్
    0.48
     pote
    0.48
     traf
    0.47
    Act Density 0.000%

    No Known Activations