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

    Neuronpedia

    INDEX
    Explanations

    interested in or like to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erca
    0.40
     joystick
    0.39
    Everything
    0.38
    更好
    0.38
     проще
    0.38
     கணி
    0.37
    ontrol
    0.37
     мъ
    0.37
     близо
    0.37
    stro
    0.36
    POSITIVE LOGITS
    これらの
    0.46
     이러한
    0.46
    このような
    0.44
     theſe
    0.44
     initiate
    0.43
     initiating
    0.43
     initiated
    0.43
     SHARE
    0.43
     participate
    0.42
     Interesse
    0.42
    Act Density 0.048%

    No Known Activations