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

    Neuronpedia

    INDEX
    Explanations

    First-person narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Poor
    -0.07
     spills
    -0.07
     intervene
    -0.07
     thần
    -0.07
    yan
    -0.07
    -material
    -0.07
     lời
    -0.07
    alarına
    -0.06
     glam
    -0.06
    .it
    -0.06
    POSITIVE LOGITS
    tiny
    0.06
    JsonIgnore
    0.06
    уляр
    0.06
    291
    0.06
    úi
    0.06
    variants
    0.06
    .paused
    0.05
    279
    0.05
    �
    0.05
    .OrderBy
    0.05
    Act Density 0.000%

    No Known Activations