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

    Neuronpedia

    INDEX
    Explanations

    | and _

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Equ
    -0.08
    uarios
    -0.07
     uid
    -0.07
     Represents
    -0.06
    ült
    -0.06
     subst
    -0.06
    Join
    -0.06
    (value
    -0.06
     rew
    -0.06
     ป
    -0.06
    POSITIVE LOGITS
     Král
    0.07
     Semiconductor
    0.06
     acl
    0.06
    032
    0.06
     Canary
    0.06
     هر
    0.06
     آم
    0.06
     learner
    0.06
    ışı
    0.06
    漂
    0.06
    Act Density 0.003%

    No Known Activations