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

    Neuronpedia

    INDEX
    Explanations

    function calls and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nesium
    0.54
    GTUIKit
    0.48
    Khokhlov
    0.47
    راعظم
    0.46
    דת
    0.45
    Გ
    0.45
     berakhir
    0.45
    ahuasca
    0.45
    ⴽ
    0.44
    🐡
    0.43
    POSITIVE LOGITS
    ↵
    0.61
     self
    0.44
     memory
    0.42
     honest
    0.40
     pred
    0.40
     (
    0.39
     this
    0.39
     left
    0.39
     Oracle
    0.39
     multi
    0.38
    Act Density 0.002%

    No Known Activations