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

    Neuronpedia

    INDEX
    Explanations

    weigh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awareness
    -0.07
    plant
    -0.07
     dps
    -0.06
     Kennedy
    -0.06
    res
    -0.06
    udents
    -0.06
    _cam
    -0.06
     VLAN
    -0.06
     desarrollo
    -0.06
    ateral
    -0.06
    POSITIVE LOGITS
    ierten
    0.06
    ~↵
    0.06
    HING
    0.06
     спе
    0.06
     belonged
    0.06
     laat
    0.06
     глу
    0.06
    UU
    0.06
    BF
    0.06
    phe
    0.06
    Act Density 0.024%

    No Known Activations