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

    Neuronpedia

    INDEX
    Explanations

    further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crews
    -0.06
    ρού
    -0.06
     mouth
    -0.06
     union
    -0.06
     mol
    -0.06
     år
    -0.06
    题
    -0.06
    กร
    -0.06
    क
    -0.06
    owns
    -0.06
    POSITIVE LOGITS
    Defined
    0.07
    ##_
    0.06
     apresent
    0.06
     Bone
    0.06
    (posts
    0.06
     estas
    0.06
     fatalError
    0.06
    %%
    0.06
     pimp
    0.06
     isValid
    0.06
    Act Density 0.002%

    No Known Activations