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

    Neuronpedia

    INDEX
    Explanations

    packing and stacking items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autonomy
    -0.07
    _loading
    -0.07
     released
    -0.07
    Message
    -0.06
     influence
    -0.06
     datasets
    -0.06
     literature
    -0.06
    _FR
    -0.06
    _cutoff
    -0.06
    Monday
    -0.06
    POSITIVE LOGITS
     아닌
    0.07
     vinc
    0.07
    ительный
    0.07
    ूट
    0.06
     podrob
    0.06
     moy
    0.06
    孔
    0.06
    vail
    0.06
     POSIX
    0.06
     biçim
    0.06
    Act Density 0.032%

    No Known Activations