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

    Neuronpedia

    INDEX
    Explanations

    code/identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    findBy
    -0.06
    нош
    -0.06
    沃
    -0.06
    .combine
    -0.06
     whilst
    -0.06
    isinin
    -0.06
     Brend
    -0.05
     intellig
    -0.05
     Navigate
    -0.05
    Navigate
    -0.05
    POSITIVE LOGITS
     podem
    0.08
    cheduling
    0.07
    .getY
    0.07
    εται
    0.07
    句
    0.07
    eless
    0.07
     sandals
    0.07
    Rooms
    0.07
     believable
    0.06
     sharpen
    0.06
    Act Density 0.000%

    No Known Activations