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

    Neuronpedia

    INDEX
    Explanations

    Feelings and emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (field
    -0.07
    .like
    -0.07
     totally
    -0.07
    pics
    -0.06
    _redirected
    -0.06
    -format
    -0.06
    σετε
    -0.06
     trucks
    -0.06
    _TV
    -0.06
         
    -0.06
    POSITIVE LOGITS
    اقتص
    0.06
     espionage
    0.06
     loneliness
    0.06
     Herb
    0.06
     getPassword
    0.06
     Admir
    0.06
     thanking
    0.06
     Sid
    0.06
     मल
    0.06
     Bug
    0.06
    Act Density 0.044%

    No Known Activations