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

    Neuronpedia

    INDEX
    Explanations

    AI names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بھر
    0.52
     علاق
    0.50
    ऱ्या
    0.49
     வித
    0.49
    жды
    0.48
     সময়
    0.48
    前者
    0.47
     विजय
    0.47
    வரது
    0.47
     극
    0.47
    POSITIVE LOGITS
     mse
    0.69
     montes
    0.68
     Bibel
    0.67
     andre
    0.67
    spoon
    0.66
     prévention
    0.65
     Holdings
    0.65
    掣
    0.65
    mites
    0.65
    hydes
    0.64
    Act Density 0.106%

    No Known Activations