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

    Neuronpedia

    INDEX
    Explanations

    paying or spending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     되
    0.59
    缢
    0.53
     කොට
    0.52
    0.51
    jTextField
    0.51
     pro
    0.51
     अगदी
    0.51
     בח
    0.50
    rás
    0.50
     much
    0.50
    POSITIVE LOGITS
     specialises
    0.80
     recognises
    0.79
    कामना
    0.77
     दिले
    0.76
    जगी
    0.73
    odisc
    0.73
     करणाऱ्या
    0.72
    bower
    0.72
    zeppelin
    0.71
     приносит
    0.71
    Act Density 0.406%

    No Known Activations