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

    Neuronpedia

    INDEX
    Explanations

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    peptide
    0.45
     Geografia
    0.39
    蹒
    0.39
    ිය
    0.38
     recorrer
    0.34
    導演
    0.34
     Fahrt
    0.34
     Sentence
    0.34
    Ꮐ
    0.34
    millan
    0.33
    POSITIVE LOGITS
     stationary
    0.48
     Stationary
    0.39
    empê
    0.38
    Terminal
    0.36
     Stopping
    0.36
     stoppage
    0.36
     întâ
    0.36
    шкой
    0.36
     terminal
    0.35
     внутрен
    0.35
    Act Density 0.136%

    No Known Activations