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

    Neuronpedia

    INDEX
    Explanations

    modules and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鋳
    0.73
     inscriptions
    0.72
     Compensation
    0.71
    compensation
    0.70
     компенса
    0.69
     ruf
    0.69
    Borderless
    0.68
     cancelación
    0.68
     compensation
    0.68
    pletion
    0.67
    POSITIVE LOGITS
     module
    2.76
    module
    2.63
     modules
    2.61
     Module
    2.53
    模块
    2.53
     Modules
    2.49
    Module
    2.46
     моду
    2.36
    modules
    2.35
    Modules
    2.27
    Act Density 0.241%

    No Known Activations