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

    Neuronpedia

    INDEX
    Explanations

    cable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     juris
    -0.07
     Ridge
    -0.07
    uur
    -0.06
     signings
    -0.06
     nová
    -0.06
     Lisa
    -0.06
    	↵
    -0.06
     isteyen
    -0.06
     technik
    -0.06
     ولد
    -0.06
    POSITIVE LOGITS
    �
    0.07
    cle
    0.06
    
    0.06
    ゲ
    0.06
    �
    0.06
    .Protocol
    0.06
     Xuân
    0.06
     Polo
    0.06
     ach
    0.06
    ông
    0.06
    Act Density 0.004%

    No Known Activations