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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zoo
    -0.06
    ко
    -0.06
    	fflush
    -0.06
    ormal
    -0.06
    arrow
    -0.06
    ніцип
    -0.06
     yazılı
    -0.06
     Mansion
    -0.06
     indirect
    -0.06
     Limit
    -0.06
    POSITIVE LOGITS
     guardar
    0.06
    ><![
    0.06
     التش
    0.06
     �
    0.06
    }>{
    0.06
     alongside
    0.06
     Amerikan
    0.06
     ant
    0.06
    .business
    0.06
     Birch
    0.06
    Act Density 0.005%

    No Known Activations