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

    Neuronpedia

    INDEX
    Explanations

    Interpersonal connection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impress
    -0.07
     Ket
    -0.07
    Postal
    -0.07
    <List
    -0.07
     money
    -0.06
    .set
    -0.06
     pv
    -0.06
    	task
    -0.06
     devices
    -0.06
     nosotros
    -0.06
    POSITIVE LOGITS
     Hamburg
    0.06
     Neue
    0.06
    ervatives
    0.06
     solitude
    0.06
    lech
    0.06
    ाइक
    0.06
     tehlik
    0.06
     interceptions
    0.06
     Dur
    0.06
    /on
    0.06
    Act Density 0.159%

    No Known Activations