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

    Neuronpedia

    INDEX
    Explanations

    specific word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rsp
    0.40
     mant
    0.40
    얕
    0.40
     PYTHONPATH
    0.39
     setattr
    0.39
     работу
    0.38
    养成
    0.37
     levando
    0.36
     enanti
    0.36
     embodying
    0.36
    POSITIVE LOGITS
    underland
    0.42
    ⇝
    0.42
    adan
    0.42
    안
    0.39
    Tren
    0.37
    远
    0.37
    Sono
    0.37
    Debut
    0.37
    uce
    0.37
    ტიკ
    0.37
    Act Density 0.001%

    No Known Activations