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

    Neuronpedia

    INDEX
    Explanations

    Gom historical isolation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    分散
    0.46
    IBAction
    0.45
    𝚎
    0.45
    ồ
    0.45
    dropBtn
    0.45
    ణ్
    0.44
     साक्षात्कार
    0.44
    čnog
    0.43
    年轻人
    0.43
    Ir
    0.42
    POSITIVE LOGITS
     hk
    0.49
     wsk
    0.47
     alleg
    0.47
     csp
    0.46
     kung
    0.45
     venu
    0.45
     tri
    0.44
     Thousand
    0.42
     csr
    0.42
    odel
    0.42
    Act Density 0.001%

    No Known Activations