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

    Neuronpedia

    INDEX
    Explanations

    Disbanding/dissolving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    писок
    -0.07
     yours
    -0.07
    -U
    -0.07
    Ï
    -0.07
    208
    -0.07
    092
    -0.07
    *u
    -0.06
    862
    -0.06
    Set
    -0.06
    -A
    -0.06
    POSITIVE LOGITS
     Seks
    0.07
    *****/↵
    0.07
    }${
    0.06
    offline
    0.06
     gm
    0.06
     Admir
    0.06
    .HE
    0.06
    _PRODUCTS
    0.06
    émon
    0.06
     Lý
    0.06
    Act Density 0.060%

    No Known Activations