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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     choses
    -0.07
    "nil
    -0.06
    .handleChange
    -0.06
    "))
    -0.06
    PARATOR
    -0.06
     بنابر
    -0.06
     lifelong
    -0.06
     kein
    -0.06
     ор
    -0.06
     allotted
    -0.06
    POSITIVE LOGITS
    emiah
    0.07
    τικού
    0.07
     Butt
    0.06
    _CENTER
    0.06
    Heart
    0.06
     posicion
    0.06
    Wall
    0.06
    _COMPANY
    0.06
    _shift
    0.06
    Mir
    0.06
    Act Density 0.000%

    No Known Activations