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

    Neuronpedia

    INDEX
    Explanations

    reproduce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fleet
    -0.07
    mention
    -0.07
     leven
    -0.07
     Occup
    -0.06
     passage
    -0.06
     �
    -0.06
    toEqual
    -0.06
     brut
    -0.06
    рав
    -0.06
    914
    -0.06
    POSITIVE LOGITS
    Explore
    0.06
     Buf
    0.06
     springs
    0.06
    .Does
    0.06
    Laughs
    0.06
    ][$
    0.06
     bitir
    0.06
     Il
    0.06
     진짜
    0.06
    圭
    0.06
    Act Density 0.000%

    No Known Activations