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

    Neuronpedia

    INDEX
    Explanations

    supervising my thesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इकाई
    0.48
    CLOUD
    0.48
    Cloud
    0.46
    CON
    0.45
    E
    0.43
    Ser
    0.43
    O
    0.43
    VES
    0.41
    П
    0.41
    EQU
    0.41
    POSITIVE LOGITS
    ложении
    0.46
    лед
    0.45
    сына
    0.45
     Audiodateien
    0.42
    猞
    0.42
    ?”.
    0.41
    脘
    0.41
    িলি
    0.41
     sechs
    0.41
    adakan
    0.41
    Act Density 0.005%

    No Known Activations