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

    Neuronpedia

    INDEX
    Explanations

    suggesting discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olyan
    0.67
    abia
    0.67
     Índ
    0.66
    ligere
    0.65
    ക്കൂ
    0.64
    ettivo
    0.63
    ək
    0.61
     logra
    0.61
    ڏ
    0.61
    ustomed
    0.60
    POSITIVE LOGITS
     criticize
    1.51
     debate
    1.37
     critique
    1.34
     criticizing
    1.34
     debated
    1.25
     criticise
    1.25
     debating
    1.21
     troubleshoot
    1.21
     complain
    1.20
     criticized
    1.19
    Act Density 0.377%

    No Known Activations