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

    Neuronpedia

    INDEX
    Explanations

    historic locations and states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Body
    0.39
    āk
    0.38
    ải
    0.38
    ów
    0.36
    itoare
    0.36
    j
    0.36
    än
    0.35
     Flügel
    0.35
    tra
    0.34
    ług
    0.34
    POSITIVE LOGITS
     texting
    0.63
     decisions
    0.51
     secession
    0.49
     waning
    0.46
     backtracking
    0.46
     unanimous
    0.46
     valuations
    0.46
     refinancing
    0.45
     situations
    0.45
     valuation
    0.45
    Act Density 0.003%

    No Known Activations