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

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ших
    -0.08
    ליך
    -0.07
     cerco
    -0.07
    odo
    -0.07
    .city
    -0.07
    ě
    -0.07
    umno
    -0.07
     GetAll
    -0.07
    (Level
    -0.07
    ize
    -0.07
    POSITIVE LOGITS
     infiltr
    0.08
    痛点
    0.07
     disappear
    0.06
     flaw
    0.06
     особ
    0.06
     pathway
    0.06
     wellbeing
    0.06
    BF
    0.06
    Limit
    0.06
     sarc
    0.06
    Act Density 0.000%

    No Known Activations