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

    Neuronpedia

    INDEX
    Explanations

    entitlement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fence
    -0.07
     lives
    -0.07
     radar
    -0.07
     scene
    -0.06
     Hack
    -0.06
     roof
    -0.06
     Safe
    -0.06
     Xavier
    -0.06
     fan
    -0.06
     reproductive
    -0.06
    POSITIVE LOGITS
     entitled
    0.13
     entitlement
    0.10
    itled
    0.08
    entic
    0.07
    inc
    0.07
    worth
    0.07
    itles
    0.07
    elt
    0.07
    nt
    0.07
    IBUT
    0.07
    Act Density 0.003%

    No Known Activations