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

    Neuronpedia

    INDEX
    Explanations

    depth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iv
    -0.07
     b
    -0.07
     prueba
    -0.07
     expresa
    -0.07
     Endless
    -0.07
     expressed
    -0.07
    Independent
    -0.07
     personnelle
    -0.07
     వ్యక్త
    -0.07
    ivan
    -0.07
    POSITIVE LOGITS
     unseen
    0.12
     profundo
    0.11
    -hidden
    0.11
    隐藏
    0.11
     verborgen
    0.11
     beneath
    0.11
    hidden
    0.11
     inaccessible
    0.11
     hidden
    0.10
    层
    0.10
    Act Density 0.033%

    No Known Activations