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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FormGroup
    -0.07
     -->↵
    -0.07
     Dickens
    -0.06
     errorThrown
    -0.06
    Forge
    -0.06
    риг
    -0.06
     misunderstanding
    -0.06
    ,/
    -0.06
    威
    -0.06
    Been
    -0.06
    POSITIVE LOGITS
    搬
    0.06
    ้ำหน
    0.06
    .WaitFor
    0.06
    .Tree
    0.06
     mask
    0.06
     HF
    0.06
      
    0.06
     ох
    0.06
    .asInstanceOf
    0.06
     Dep
    0.06
    Act Density 0.009%

    No Known Activations