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

    Neuronpedia

    INDEX
    Explanations

    shell commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *
    1.11
     //
    1.01
     **
    0.99
     ***
    0.96
     \*
    0.92
     /
    0.91
     *_
    0.87
     *=
    0.84
     $/
    0.81
     *\
    0.77
    POSITIVE LOGITS
     मणिपुर
    0.80
    calls
    0.73
    拦
    0.73
    வருக
    0.71
     चैम्पियन
    0.70
    ul
    0.70
     मतदाता
    0.70
     což
    0.70
    λη
    0.69
     पुअनि
    0.69
    Act Density 0.042%

    No Known Activations