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

    Neuronpedia

    INDEX
    Explanations

    befriend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    E
    -0.07
    *u
    -0.07
    _anchor
    -0.07
    _video
    -0.07
    _clients
    -0.07
    	StringBuilder
    -0.06
     payday
    -0.06
     Thursday
    -0.06
     sucht
    -0.06
     Э
    -0.06
    POSITIVE LOGITS
     망
    0.07
    gtk
    0.06
    patibility
    0.06
    LOOK
    0.06
    (tensor
    0.06
     spear
    0.06
    ツ
    0.06
    惑
    0.06
    하는데
    0.06
    YST
    0.06
    Act Density 0.007%

    No Known Activations