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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hass
    -0.10
    fffffff
    -0.10
    abcdefghijklmnop
    -0.09
    abcdefghijkl
    -0.09
    xd
    -0.09
     Dillon
    -0.09
    Looper
    -0.09
    WARDED
    -0.08
     Mobility
    -0.08
    rift
    -0.08
    POSITIVE LOGITS
     ab
    0.15
     AB
    0.13
    123
    0.13
    AB
    0.12
    #ab
    0.12
     AABB
    0.11
    012
    0.11
    ab
    0.11
    аб
    0.11
    cba
    0.10
    Act Density 0.166%

    No Known Activations