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

    Neuronpedia

    INDEX
    Explanations

    mentor, mentoring, mentorship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ong
    1.30
    ag
    1.16
    í
    1.11
    ী
    1.09
    as
    1.09
    িন
    1.07
    ни
    1.06
    in
    1.05
    it
    1.05
    াল
    0.99
    POSITIVE LOGITS
    ;
    1.62
     mentoring
    1.41
     mentor
    1.24
     mentors
    1.16
     mentorship
    1.09
    Mentor
    1.07
     Mentor
    1.02
    ;*/
    1.00
    ],
    0.98
    ;//
    0.97
    Act Density 0.004%

    No Known Activations