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

    Neuronpedia

    INDEX
    Explanations

    javax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ================================================
    -0.07
     �
    -0.07
    zer
    -0.07
    Assignable
    -0.06
    Center
    -0.06
     triggered
    -0.06
     cri
    -0.06
     PAL
    -0.06
    Project
    -0.06
    ician
    -0.06
    POSITIVE LOGITS
     judiciary
    0.07
     bargaining
    0.07
     заболеваний
    0.06
    abc
    0.06
     naw
    0.06
     stayed
    0.06
    هم
    0.06
     Zheng
    0.06
    PHONE
    0.06
     lavish
    0.06
    Act Density 0.001%

    No Known Activations