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

    Neuronpedia

    INDEX
    Explanations

    notes and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inroads
    1.01
     troviamo
    0.93
    albeit
    0.93
     meagre
    0.86
     unscathed
    0.84
     ieri
    0.84
     ganhou
    0.83
    算是
    0.83
     philosopher
    0.82
     conocemos
    0.82
    POSITIVE LOGITS
    Remember
    1.57
    Tips
    1.56
     Remember
    1.44
    注意事项
    1.42
     Tips
    1.36
    Customize
    1.33
    Before
    1.30
     remember
    1.27
    Use
    1.26
    注意事項
    1.26
    Act Density 0.234%

    No Known Activations