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

    Neuronpedia

    INDEX
    Explanations

    subscription

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    村
    -0.07
     crispy
    -0.07
    岛
    -0.07
    —he
    -0.07
    ;?>↵
    -0.07
     breakpoint
    -0.06
    ما
    -0.06
     Differential
    -0.06
    beck
    -0.06
    ravel
    -0.06
    POSITIVE LOGITS
     (^
    0.07
     Birth
    0.06
     retiring
    0.06
     nád
    0.06
     tub
    0.06
     checker
    0.06
     penet
    0.06
     urging
    0.06
     Lucia
    0.06
     register
    0.06
    Act Density 0.005%

    No Known Activations