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

    Neuronpedia

    INDEX
    Explanations

    Cam

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ोर
    -0.07
    Workers
    -0.06
     MR
    -0.06
    ?↵↵↵↵↵↵
    -0.06
    ंतर
    -0.06
    ;'↵
    -0.06
    )↵↵↵↵↵
    -0.06
    _NOT
    -0.06
     переп
    -0.06
    -T
    -0.06
    POSITIVE LOGITS
     ceny
    0.07
     chức
    0.07
     朝
    0.06
     scram
    0.06
    leo
    0.06
     emotions
    0.06
     pours
    0.06
    訴
    0.06
    (common
    0.06
    Caught
    0.06
    Act Density 0.004%

    No Known Activations