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

    Neuronpedia

    INDEX
    Explanations

    chemical manufacturing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     animal
    -0.07
     mut
    -0.07
     Pennsylvania
    -0.06
     playful
    -0.06
     loc
    -0.06
     Yine
    -0.06
     viz
    -0.06
     thrive
    -0.06
     HOW
    -0.06
     Ein
    -0.06
    POSITIVE LOGITS
     }}"
    0.06
    Blocked
    0.06
    \_
    0.06
     грав
    0.06
    的心
    0.06
    وث
    0.05
    木
    0.05
    �
    0.05
     ribs
    0.05
     Redistributions
    0.05
    Act Density 0.010%

    No Known Activations