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

    Neuronpedia

    INDEX
    Explanations

    code/technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.06
    grand
    -0.06
     photographers
    -0.06
     bending
    -0.06
     angles
    -0.06
    achines
    -0.06
    atLng
    -0.06
     producers
    -0.06
     blends
    -0.06
    .mag
    -0.06
    POSITIVE LOGITS
     Derrick
    0.08
     Теп
    0.07
    .ERR
    0.06
     Denied
    0.06
     رق
    0.06
     ++)↵
    0.06
    Rocket
    0.06
     trades
    0.06
     WOM
    0.06
     escalate
    0.06
    Act Density 0.000%

    No Known Activations