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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fin
    -0.06
    ита
    -0.06
     электр
    -0.06
    olicited
    -0.06
    prises
    -0.06
    ][:
    -0.06
    ices
    -0.06
    volent
    -0.06
     Who
    -0.06
    百
    -0.06
    POSITIVE LOGITS
     glGen
    0.07
    onedDateTime
    0.07
     bastard
    0.07
    _song
    0.07
    Fig
    0.06
     Billing
    0.06
     interviews
    0.06
     Euros
    0.06
     ListItem
    0.06
     colleagues
    0.06
    Act Density 0.036%

    No Known Activations