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

    Neuronpedia

    INDEX
    Explanations

    behavioral science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     price
    -0.07
     مكان
    -0.06
    法人
    -0.06
     dinero
    -0.06
    ([
    -0.06
     radius
    -0.06
     stored
    -0.06
     Silver
    -0.06
    价格
    -0.06
     prend
    -0.06
    POSITIVE LOGITS
    εια
    0.07
     bent
    0.07
    \Repositories
    0.07
    elect
    0.06
    Shortcut
    0.06
    phant
    0.06
     bổ
    0.06
     proved
    0.06
    	c
    0.06
    えて
    0.06
    Act Density 0.006%

    No Known Activations