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

    Neuronpedia

    INDEX
    Explanations

    appearing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	switch
    -0.07
     adoption
    -0.07
    ragen
    -0.07
     предостав
    -0.07
    メッ
    -0.07
     ExecutionContext
    -0.07
     paciente
    -0.06
    établ
    -0.06
    .Id
    -0.06
     ציבור
    -0.06
    POSITIVE LOGITS
    %%
    0.08
    global
    0.07
    \Session
    0.07
     researched
    0.07
    =.
    0.07
    始
    0.07
    调研
    0.07
    不利于
    0.07
    🐚
    0.07
    nw
    0.07
    Act Density 0.001%

    No Known Activations