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

    Neuronpedia

    INDEX
    Explanations

    return list or manage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mast
    0.43
     rockers
    0.40
     reb
    0.38
     sharps
    0.38
     pector
    0.38
     kap
    0.37
     rys
    0.37
     mel
    0.37
     swe
    0.37
     masts
    0.36
    POSITIVE LOGITS
    稳定的
    0.40
    创
    0.38
    银
    0.37
    ModuleManager
    0.37
    加上
    0.36
     ஒரே
    0.36
    Projeto
    0.36
    简单
    0.36
    注册
    0.35
    եց
    0.35
    Act Density 0.000%

    No Known Activations