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

    Neuronpedia

    INDEX
    Explanations

    orientation/direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     นาย
    -0.06
     replication
    -0.06
    thus
    -0.06
     Nuclear
    -0.06
     Zum
    -0.06
    @Transactional
    -0.06
     кноп
    -0.06
    .addValue
    -0.05
     Werk
    -0.05
    tains
    -0.05
    POSITIVE LOGITS
     سان
    0.07
     entra
    0.07
     대해
    0.07
     poss
    0.07
    规模
    0.07
    ौद
    0.07
    	glog
    0.06
    GU
    0.06
    ective
    0.06
    メント
    0.06
    Act Density 0.005%

    No Known Activations