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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
        	↵
    -0.07
    말
    -0.06
    InstanceOf
    -0.06
     pun
    -0.06
     συμμε
    -0.06
    =p
    -0.06
    ---------------↵
    -0.06
    "name
    -0.06
    单位
    -0.06
    _vlan
    -0.06
    POSITIVE LOGITS
     missionaries
    0.07
    iser
    0.07
    iz
    0.07
    ocup
    0.06
    ící
    0.06
    fresh
    0.06
     routines
    0.06
    _uint
    0.06
    didn
    0.06
     KT
    0.06
    Act Density 0.000%

    No Known Activations