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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "L
    -0.07
     typography
    -0.07
     sens
    -0.07
     이번
    -0.06
     زیب
    -0.06
     батар
    -0.06
     contradiction
    -0.06
    ุข
    -0.06
     BaseType
    -0.06
     sei
    -0.06
    POSITIVE LOGITS
    acing
    0.07
    .textLabel
    0.07
    ovat
    0.06
    ():↵
    0.06
    .Item
    0.06
     Welsh
    0.06
     honored
    0.06
    lobals
    0.06
    cour
    0.06
     milan
    0.06
    Act Density 0.000%

    No Known Activations