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

    Neuronpedia

    INDEX
    Explanations

    logical statements and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     formalism
    0.51
     structure
    0.49
     biochemistry
    0.48
     plasma
    0.47
     chronology
    0.47
     adhes
    0.47
     microstructure
    0.46
     physiology
    0.46
     clinique
    0.46
     medical
    0.45
    POSITIVE LOGITS
     દરમ
    0.48
    ările
    0.48
    पिछ
    0.47
    Lastly
    0.47
    ؟
    0.46
    owała
    0.45
    NORTH
    0.45
    LError
    0.44
    că
    0.44
    ポール
    0.44
    Act Density 0.001%

    No Known Activations