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

    Neuronpedia

    INDEX
    Explanations

    water rescues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conn
    -0.07
     rh
    -0.06
    ρά
    -0.06
     nas
    -0.06
    ثير
    -0.06
     vál
    -0.06
     Gill
    -0.06
     Conscious
    -0.06
     SETTINGS
    -0.06
     deter
    -0.06
    POSITIVE LOGITS
     بپ
    0.07
    -memory
    0.06
    �
    0.06
    쉬
    0.06
    -record
    0.06
    /class
    0.06
     Ellie
    0.06
    history
    0.06
     iterate
    0.06
     зі
    0.06
    Act Density 0.021%

    No Known Activations