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

    Neuronpedia

    INDEX
    Explanations

    NOW, THEREFORE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DropdownBox
    0.40
     sprouting
    0.39
     immers
    0.38
     leaching
    0.38
     উপরের
    0.38
    உலகின்
    0.38
     setShow
    0.38
    क्यूमेंट
    0.37
    ่าว
    0.37
     betta
    0.37
    POSITIVE LOGITS
    Appellant
    0.41
    fprintf
    0.40
    error
    0.39
     Appellant
    0.39
    iv
    0.38
    we
    0.38
    MEM
    0.37
    FAILED
    0.37
     terzo
    0.37
    First
    0.37
    Act Density 0.005%

    No Known Activations