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

    Neuronpedia

    INDEX
    Explanations

    Relative clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ething
    -0.07
    �
    -0.07
    (character
    -0.06
     акт
    -0.06
    posting
    -0.06
     ดาว
    -0.06
     bal
    -0.06
    ्तम
    -0.06
     carriage
    -0.06
    .pose
    -0.06
    POSITIVE LOGITS
    -choice
    0.07
     lif
    0.06
     Minority
    0.06
    χρι
    0.06
     scri
    0.06
     valued
    0.06
     desenv
    0.06
    _MIX
    0.06
     možnost
    0.06
     İngiltere
    0.06
    Act Density 0.122%

    No Known Activations