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

    Neuronpedia

    INDEX
    Explanations

    abstract, attract, accelerate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     потребуется
    0.51
     хотят
    0.51
     gyak
    0.50
    酆
    0.50
    },\
    0.49
     ogrod
    0.49
     हाइट
    0.49
     gradioApp
    0.49
    <unused740>
    0.48
    ága
    0.48
    POSITIVE LOGITS
    s
    0.40
     Spearman
    0.39
     Labor
    0.39
    lipid
    0.38
    ну
    0.38
    ریق
    0.37
    INFE
    0.36
    omeres
    0.35
    ίδ
    0.35
    伯
    0.35
    Act Density 0.008%

    No Known Activations