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

    Neuronpedia

    INDEX
    Explanations

    Words ending in "ed"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marg
    -0.07
     Patient
    -0.07
    ataloader
    -0.07
     kayak
    -0.07
    washer
    -0.06
    bg
    -0.06
    .OneToOne
    -0.06
     професси
    -0.06
     Recipe
    -0.06
     KP
    -0.06
    POSITIVE LOGITS
    UED
    0.08
    \Doctrine
    0.07
     Reno
    0.06
    �
    0.06
    575
    0.06
     dishonest
    0.06
    ♠
    0.06
    セン
    0.06
     subsidiary
    0.06
    /groups
    0.06
    Act Density 0.002%

    No Known Activations