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

    Neuronpedia

    INDEX
    Explanations

    direction, AU, flagella

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.69
    ρική
    0.67
    د
    0.63
    ry
    0.61
    мі
    0.59
    据说
    0.57
    ik
    0.57
    ly
    0.56
    ez
    0.56
    sell
    0.54
    POSITIVE LOGITS
     netizens
    0.61
    AL
    0.57
    AK
    0.55
    OU
    0.54
    NeedConnect
    0.53
     அவ்வ
    0.52
     ਸ
    0.51
     locals
    0.51
    佇
    0.51
     שא
    0.50
    Act Density 0.001%

    No Known Activations