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

    Neuronpedia

    INDEX
    Explanations

    can perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stadium
    0.46
     جریان
    0.44
     documentaire
    0.43
    椹
    0.41
     empezamos
    0.40
     aqueous
    0.40
     başlayalım
    0.38
     empie
    0.38
    ജ്
    0.38
     precedent
    0.37
    POSITIVE LOGITS
     plug
    1.08
     Plug
    0.96
     plugged
    0.95
    Plug
    0.91
    plug
    0.89
     plugging
    0.79
     plugs
    0.77
     input
    0.77
     paste
    0.77
     Plugging
    0.74
    Act Density 0.013%

    No Known Activations