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

    Neuronpedia

    INDEX
    Explanations

    man

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zv
    -0.07
    によ
    -0.06
     又
    -0.06
    -keys
    -0.06
     zdarma
    -0.06
    Prop
    -0.06
     gotta
    -0.06
    defines
    -0.06
     Defines
    -0.06
     ศ
    -0.06
    POSITIVE LOGITS
     ICE
    0.08
    Requirements
    0.07
    646
    0.07
    bread
    0.07
    GE
    0.07
     Senate
    0.06
     DIRECT
    0.06
     STILL
    0.06
     Korea
    0.06
    895
    0.06
    Act Density 0.000%

    No Known Activations