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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts easily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്കിയി
    0.33
     prepar
    0.32
     caters
    0.32
     publicit
    0.32
     authorize
    0.31
    ക്കാല
    0.31
     stipend
    0.31
     offline
    0.30
    aptops
    0.30
    চ্চার
    0.30
    POSITIVE LOGITS
    好奇
    0.40
     जेव्हा
    0.37
     आणि
    0.36
    शे
    0.35
    ००
    0.35
     और
    0.35
     ถ
    0.35
     cuidadosamente
    0.35
    幽
    0.35
     અને
    0.35
    Act Density 0.001%

    No Known Activations