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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UserInfo
    -0.07
    都会
    -0.06
    Height
    -0.06
     Rock
    -0.06
    aga
    -0.06
     Choice
    -0.06
     умови
    -0.06
     SMB
    -0.06
    Nation
    -0.06
    واج
    -0.06
    POSITIVE LOGITS
     встре
    0.07
    JOR
    0.07
    .</
    0.06
     Lawn
    0.06
     amazing
    0.06
    靠
    0.06
    原始
    0.06
     compliant
    0.06
    numerusform
    0.06
    urved
    0.06
    Act Density 0.014%

    No Known Activations