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

    Neuronpedia

    INDEX
    Explanations

    appearance compliments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    216
    -0.08
    peater
    -0.07
    ISP
    -0.06
    Decrypt
    -0.06
     "*"
    -0.06
     Pistol
    -0.06
     startup
    -0.06
    rewrite
    -0.06
    kills
    -0.06
     waive
    -0.06
    POSITIVE LOGITS
     overlooking
    0.07
    UNKNOWN
    0.07
     могут
    0.07
    lasyon
    0.06
    /cart
    0.06
    ropdown
    0.06
     داخل
    0.06
     termed
    0.06
    .Convert
    0.06
     Friend
    0.06
    Act Density 0.024%

    No Known Activations