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

    Neuronpedia

    INDEX
    Explanations

    connecting and displaying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngth
    0.44
    をや
    0.39
    pá
    0.39
    eiros
    0.38
    ন্দ্ব
    0.37
    镖
    0.37
    isetas
    0.37
    elled
    0.37
    reement
    0.37
    ≜
    0.37
    POSITIVE LOGITS
    Connect
    0.56
     Connect
    0.54
     connects
    0.54
     connecting
    0.50
    connect
    0.49
     connect
    0.48
     Connecting
    0.45
     connecter
    0.44
     conect
    0.43
     connections
    0.42
    Act Density 0.001%

    No Known Activations