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

    Neuronpedia

    INDEX
    Explanations

    emphasis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عراق
    -0.07
    VERAGE
    -0.07
     중요
    -0.07
     एज
    -0.06
     часом
    -0.06
    togroup
    -0.06
    라도
    -0.06
    یری
    -0.06
     صد
    -0.06
     module
    -0.06
    POSITIVE LOGITS
    ?]
    0.08
    ิส
    0.07
    .LogInformation
    0.07
    Beans
    0.06
    Bid
    0.06
    loggedIn
    0.06
    -init
    0.06
    acomment
    0.06
    ajaran
    0.06
     hr
    0.06
    Act Density 0.098%

    No Known Activations