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
    partner
    -0.07
     güçlü
    -0.07
    ctp
    -0.07
     maintaining
    -0.07
     eğitim
    -0.07
    gas
    -0.07
    _Profile
    -0.06
    _attrib
    -0.06
    	alert
    -0.06
    Cert
    -0.06
    POSITIVE LOGITS
     extraordin
    0.08
     inflicted
    0.06
    -indent
    0.06
     празд
    0.06
    <()>
    0.06
    .Slf
    0.06
    _xlim
    0.06
    ενο
    0.06
    .Exit
    0.06
    (Response
    0.06
    Act Density 0.014%

    No Known Activations