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

    Neuronpedia

    INDEX
    Explanations

    mix, benefit, fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Converter
    0.58
    Converting
    0.54
    Constants
    0.52
    Service
    0.49
    Server
    0.48
    Globals
    0.48
     उपास
    0.47
    NetAmount
    0.47
     CLASSES
    0.47
    মুর
    0.46
    POSITIVE LOGITS
    0.61
    ే
    0.56
    eep
    0.52
     со
    0.51
    цени
    0.50
    е
    0.50
     phylogenetic
    0.50
    oc
    0.49
    ag
    0.49
    azione
    0.49
    Act Density 0.000%

    No Known Activations