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

    Neuronpedia

    INDEX
    Explanations

    Newlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Comparator
    -0.07
     insets
    -0.07
     portraying
    -0.07
     analyzing
    -0.07
     getDate
    -0.06
    يلاد
    -0.06
     αρχ
    -0.06
    _BT
    -0.06
    Joined
    -0.06
    except
    -0.06
    POSITIVE LOGITS
    同步
    0.07
    賀
    0.06
     Ivory
    0.06
    ASI
    0.06
    ционной
    0.06
    ].[
    0.06
    [^
    0.06
     mình
    0.06
    sko
    0.06
     پوست
    0.06
    Act Density 0.001%

    No Known Activations