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

    Neuronpedia

    INDEX
    Explanations

    SQL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moral
    -0.07
    CRY
    -0.07
    MMdd
    -0.06
     antidepress
    -0.06
     defensively
    -0.06
    ự
    -0.06
    ⽼
    -0.06
    ensively
    -0.06
    -0.06
     מפתח
    -0.06
    POSITIVE LOGITS
    _id
    0.08
     php
    0.07
     נוס
    0.07
     boat
    0.06
    _utf
    0.06
    あ
    0.06
     ascertain
    0.06
    ata
    0.06
    Tk
    0.06
    ü
    0.06
    Act Density 0.001%

    No Known Activations