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

    Neuronpedia

    INDEX
    Explanations

    Yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACIÓN
    -0.06
     trưởng
    -0.06
    Directive
    -0.05
    Industry
    -0.05
     어려
    -0.05
    _watch
    -0.05
    lish
    -0.05
    alian
    -0.05
    orgot
    -0.05
    lessness
    -0.05
    POSITIVE LOGITS
     Yes
    0.09
    “Yes
    0.07
     stamina
    0.07
    "Yes
    0.07
    PosY
    0.07
     yes
    0.07
     EXPECT
    0.06
     usern
    0.06
     yiy
    0.06
    での
    0.06
    Act Density 0.036%

    No Known Activations