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

    Neuronpedia

    INDEX
    Explanations

    calls for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     always
    1.04
    每年
    0.95
     siempre
    0.93
     your
    0.93
     annually
    0.88
     year
    0.84
     Always
    0.84
    近年
    0.83
     promotes
    0.82
    always
    0.80
    POSITIVE LOGITS
     sobbing
    1.21
     rescuers
    1.16
     চিৎকার
    1.15
     وكان
    1.13
    救援
    1.13
     ঘটনাস্থ
    1.11
     وكانت
    1.10
     paramedics
    1.08
    消防
    1.07
     commotion
    1.07
    Act Density 0.320%

    No Known Activations