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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mobility
    -0.07
    Coverage
    -0.07
     piston
    -0.06
    Fish
    -0.06
    .partner
    -0.06
    роч
    -0.06
     NSString
    -0.06
     prefect
    -0.06
    Containers
    -0.06
     UserRole
    -0.06
    POSITIVE LOGITS
    ENDED
    0.07
    اسات
    0.07
    た
    0.07
    �
    0.06
    Scotland
    0.06
    isiyle
    0.06
    OTH
    0.06
     staging
    0.06
     Sloven
    0.06
     grands
    0.06
    Act Density 0.014%

    No Known Activations