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

    Neuronpedia

    INDEX
    Explanations

    depression, loss of interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    League
    -0.08
    Numer
    -0.08
     Maschinen
    -0.08
     Laat
    -0.08
     Indones
    -0.08
     Maschine
    -0.08
     chip
    -0.07
     Numer
    -0.07
    Autores
    -0.07
    .Butter
    -0.07
    POSITIVE LOGITS
     αγα
    0.08
    вати
    0.08
     Love
    0.08
     کردن
    0.08
     love
    0.08
     binocular
    0.08
    amphetamine
    0.08
    กิจ
    0.08
     zor
    0.07
     અભ
    0.07
    Act Density 0.001%

    No Known Activations