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

    Neuronpedia

    INDEX
    Explanations

    web technologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cells
    -0.07
     enthusi
    -0.07
     venue
    -0.07
     sublicense
    -0.07
     blocked
    -0.07
    role
    -0.07
    Ctrl
    -0.06
    '^
    -0.06
     term
    -0.06
     Keith
    -0.06
    POSITIVE LOGITS
     unfair
    0.07
     laundering
    0.06
     употреб
    0.06
     wishes
    0.06
     bö
    0.06
    ISTRY
    0.06
    guided
    0.06
    ุลาคม
    0.06
     judgments
    0.06
     conquest
    0.06
    Act Density 0.013%

    No Known Activations