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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    다
    0.55
    ه
    0.47
     hopp
    0.41
    да
    0.40
    дый
    0.39
    ным
    0.37
    هان
    0.37
    ва
    0.37
     bess
    0.37
     Бер
    0.37
    POSITIVE LOGITS
    ST
    0.45
    ately
    0.42
    ajuan
    0.41
     Chauhan
    0.40
    uses
    0.39
     वाक्य
    0.39
    ?")
    0.39
    ates
    0.38
     ambil
    0.38
    VPN
    0.38
    Act Density 0.008%

    No Known Activations