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

    Neuronpedia

    INDEX
    Explanations

    partial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    饥
    -0.08
     describes
    -0.08
     jorn
    -0.06
    ثم
    -0.06
     נשמע
    -0.06
    -focus
    -0.06
    üyü
    -0.06
     wyświet
    -0.06
     murderers
    -0.06
     portray
    -0.06
    POSITIVE LOGITS
    Robot
    0.07
    .hadoop
    0.07
     battling
    0.07
     شيئا
    0.06
    אט
    0.06
    mètre
    0.06
    .uniform
    0.06
    .shadow
    0.06
     coral
    0.06
     Mister
    0.06
    Act Density 0.000%

    No Known Activations