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

    Neuronpedia

    INDEX
    Explanations

    alternative languages and finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mentally
    0.39
     leaves
    0.37
     openly
    0.37
     going
    0.37
    தாக
    0.36
     one
    0.36
     Even
    0.36
     seasonally
    0.36
     Bes
    0.35
     belongs
    0.35
    POSITIVE LOGITS
     loans
    0.47
     prést
    0.46
     alternative
    0.46
    信用卡
    0.45
    alternative
    0.45
     kredit
    0.45
     เธอ
    0.45
    ्मी
    0.44
     वैकल्पिक
    0.44
    貸款
    0.44
    Act Density 0.000%

    No Known Activations