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

    Neuronpedia

    INDEX
    Explanations

    offering options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dundee
    1.31
     Griechen
    1.31
     Cardiff
    1.30
     Perth
    1.28
     Sark
    1.28
    éroport
    1.28
     Dink
    1.27
     ग्रामीण
    1.26
     Australien
    1.26
     Duitse
    1.24
    POSITIVE LOGITS
    По
    0.86
    ~$
    0.84
    по
    0.83
    เหนือ
    0.83
    !
    0.82
     with
    0.81
     beginning
    0.81
    !\
    0.81
    还是
    0.80
    Пред
    0.79
    Act Density 0.013%

    No Known Activations