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

    Neuronpedia

    INDEX
    Explanations

    setting os environment variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пет
    0.44
    ("@
    0.39
     Specialist
    0.38
     SME
    0.38
     Verst
    0.38
     коре
    0.38
    jede
    0.37
     тә
    0.37
     Discrimin
    0.36
     ["
    0.36
    POSITIVE LOGITS
    ifolium
    0.43
     Mathf
    0.41
    reu
    0.40
     Idiot
    0.40
     steep
    0.39
     ሥ
    0.39
    zyb
    0.39
    wärt
    0.37
     wher
    0.37
    ifford
    0.37
    Act Density 0.000%

    No Known Activations