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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Four
    -0.07
     viewpoint
    -0.07
    Soup
    -0.06
     Plants
    -0.06
    .Configuration
    -0.06
    veyor
    -0.06
    >v
    -0.06
     Operator
    -0.06
     Weapon
    -0.06
     Film
    -0.06
    POSITIVE LOGITS
    SCALL
    0.07
    bery
    0.07
     cheap
    0.07
    ğit
    0.07
    ند
    0.06
    adal
    0.06
    cname
    0.06
    !<
    0.06
    WAIT
    0.06
     폐
    0.06
    Act Density 0.109%

    No Known Activations