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

    Neuronpedia

    INDEX
    Explanations

    onomy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EATURE
    -0.06
    ussion
    -0.06
    C
    -0.06
    =q
    -0.06
    (weight
    -0.06
    -byte
    -0.06
    ~=
    -0.06
    -defined
    -0.06
    ріб
    -0.06
    Device
    -0.06
    POSITIVE LOGITS
    outed
    0.07
     plausible
    0.07
    IClient
    0.06
     Ze
    0.06
     DAM
    0.06
     прог
    0.06
    олит
    0.06
     Anderson
    0.06
    >".$
    0.06
    	work
    0.06
    Act Density 0.001%

    No Known Activations